README.md

metadata

license: cc-by-nc-4.0

Gemma Scope

TODO add GIF here.

This is a landing page for Gemma Scope, a comprehensive, open suite of sparse autoencoders for Gemma 2 9B and 2B. Sparse autoencoders are a "microscope" of sorts that can help us break down a model’s internal activations into the underlying concepts, just as biologists use microscopes to study the individual cells of plants and animals.

Key links:

• Learn more about Gemma Scope on the Google DeepMind blog (TODO link)
• Check out the interactive Gemma Scope demo made by Neuronpedia.
• Check out our coding tutorial for how to use Gemma Scope (TODO link)
• Read the Gemma Scope technical report (TODO link)
• Check out Mishax, an internal tool we used to help make Gemma Scope (TODO link)

Download Gemma Scope here:

TODO make table