Update README.md

README.md

@@ -4,7 +4,7 @@ license: cc-by-nc-4.0
 
 # Gemma Scope:
 
-!(Gemma Scope 002 - 16-9.gif)
+![](gemma_scope.gif)
 
 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.
 
@@ -14,7 +14,7 @@ This is a landing page for **Gemma Scope**, a comprehensive, open suite of spars
 - Check out the [interactive Gemma Scope demo](https://www.neuronpedia.org/gemma-scope) made by [Neuronpedia](https://www.neuronpedia.org/).
 - Check out our [Google Colab notebook tutorial](https://colab.research.google.com/drive/17dQFYUYnuKnP6OwQPH9v_GSYUW5aj-Rp?ts=66a77041) for how to use Gemma Scope.
 - Read the Gemma Scope technical report (TODO link).
-- Check out Mishax, an internal tool we used to help make Gemma Scope (TODO link).
+- Check out [Mishax](https://github.com/google-deepmind/mishax), a GDM internal tool that we used in this projec to exposing the internal activations inside Gemma 2 models.
 
 # Quick start: