Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog/Podcast
NEW
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/Podcast
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Initial Gemma-2B SAEs
Gemma-2B
Residual Stream
6-RES-JB
4446
Prev
Next
MODEL
6-res-jb
Source/SAE
INDEX
Go
Explanations
technical information related to computer devices and settings
oai_token-act-pair · gpt-3.5-turbo
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Configuration
jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
HuggingFaceFW/fineweb
Features
16,384
Data Type
torch.float32
Hook Point
blocks.6.hook_resid_post
Architecture
standard
Context Size
1,024
Dataset
HuggingFaceFW/fineweb
Hook Point Layer
6
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2b/6-res-jb/4446?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2b/6-res-jb/4446?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Neuron Alignment
Index
Value
% of L₁
50
+0.20
1.2%
1133
+0.14
0.8%
521
+0.10
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1133
+0.20
0.05
521
+0.14
0.04
1096
+0.10
0.03
Negative Logits
<bos>
-3.00
ⓧ
-1.15
/**
-1.02
-1.01
/***
-0.93
springfox
-0.90
<?
-0.88
/*!
-0.74
//*/
-0.73
/*
-0.68
POSITIVE LOGITS
[
1.04
$[
0.85
[
0.83
([
0.81
thuy
0.78
=[
0.78
()[
0.77
-[
0.77
corrom
0.77
>[
0.77
Act
ivations
Density 0.063%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
