AI Lab Goodfire Raises $150M at $1.25B Valuation to Design Models with Interpretability
webGoodfire is an AI interpretability research lab that raised $150M Series B to advance mechanistic interpretability research, enabling AI model steering, safety improvements, and scientific discovery — directly relevant to AI safety through understanding neural network internals.
Metadata
Importance: 52/100press releasenews
Summary
Goodfire, an AI research lab focused on mechanistic interpretability, announced a $150M Series B funding round at a $1.25B valuation. The company uses interpretability techniques to understand, debug, and intentionally design AI models, with applications in model safety and scientific discovery. Notable achievements include identifying a novel class of Alzheimer's biomarkers by reverse-engineering a foundation model.
Key Points
- •Goodfire raised $150M Series B led by B Capital, with participation from Lightspeed, Menlo Ventures, Salesforce Ventures, Eric Schmidt, and others.
- •The company focuses on mechanistic interpretability to understand neural network internals, enabling intentional model design rather than black-box development.
- •Goodfire applied interpretability to an epigenetic model to identify a novel class of Alzheimer's biomarkers — a first for reverse-engineering a foundation model in natural sciences.
- •The lab positions interpretability as foundational science for AI, analogous to thermodynamics for steam engines, enabling safer and more steerable AI systems.
- •Goodfire is part of an emerging 'neolab' movement pursuing research neglected by large scaling labs like OpenAI and Google DeepMind.
Cached Content Preview
HTTP 200Fetched Apr 9, 20268 KB
AI Lab Goodfire Raises $150M at $1.25B Valuation to Design Models with Interpretability
Accessibility Statement
Skip Navigation
SAN FRANCISCO , Feb. 5, 2026 /PRNewswire/ -- Today, Goodfire —the AI research lab using interpretability to understand, learn from, and design models—announced a $150 million Series B funding round at a $1.25 billion valuation. The round was led by B Capital, with participation from existing investors Juniper Ventures, Menlo Ventures, Lightspeed Venture Partners, South Park Commons, and Wing Venture Capital, and new investors DFJ Growth, Salesforce Ventures, Eric Schmidt, and others. This funding, coming less than a year after its Series A, will enable Goodfire to advance frontier research initiatives, build the next generation of its core product, and scale partnerships across AI agents and life sciences.
Interpretability is the science of how neural networks work internally, and how modifying their inner mechanisms can shape their behavior—e.g., adjusting a reasoning model's internal concepts to change how it thinks and responds. Interpretability also enables AI-to-human knowledge transfer, i.e., extracting novel insights from powerful AI models. Goodfire recently identified a novel class of Alzheimer's biomarkers in this way, by applying interpretability techniques to an epigenetic model built by Prima Mente—the first major finding in the natural sciences obtained from reverse-engineering a foundation model.
"We are building the most consequential technology of our time without a true understanding of how to design models that do what we want," said Yan-David "Yanda" Erlich, former COO and CRO at Weights & Biases and General Partner at B Capital. "At Weights & Biases, I watched thousands of ML teams struggle with the same fundamental problem: they could track their experiments and monitor their models, but they couldn't truly understand why their models behaved the way they did. Bridging that gap is the next frontier. Goodfire is unlocking the ability to truly steer what models learn, make them safer and more useful, and extract the vast knowledge they contain."
Most companies building AI models today build their models as black boxes. Goodfire believes that that approach means that society is currently flying blind—and that deeply understanding how models work "under the hood" is critical to building and deploying safe, powerful AI systems. The company is pursuing research which turns AI into something that can be understood, debugged, and intentionally designed like written software.
"Interpretability, for us, is the toolset for a new domain of science: a way to form hypotheses, run experiments, and ultimately design intelligence rather than stumbling into it," explained Goodfire CEO
... (truncated, 8 KB total)Resource ID:
1bc3d435f1913ca3 | Stable ID: sid_5phiF1XG5g