Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Steer
SAE Evals
Blog
Slack
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog/RSS
GitHub
Slack
Twitter
Contact
Home
Joseph Bloom · Initial Gemma-2B SAEs
Gemma-2B
Residual Stream
6-RES-JB
14
Prev
Next
MODEL
6-res-jb
Source/SAE
INDEX
Go
Explanations
phrases related to toys and toy sales
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/14?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/14?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
+0.17
1.0%
1416
+0.12
0.7%
406
+0.11
0.6%
Correlated Neurons
Index
P. Corr.
Cos Sim.
1416
+0.17
0.03
406
+0.12
0.02
1778
+0.11
0.03
Negative Logits
<bos>
-2.90
ⓧ
-1.04
-0.97
intersper
-0.94
/**
-0.93
<?
-0.93
disbur
-0.86
defray
-0.83
/***
-0.82
/*!
-0.70
POSITIVE LOGITS
toys
1.30
toy
1.28
Toy
1.24
Toy
1.21
Toys
1.12
toy
1.09
TOY
1.07
Toys
1.06
toys
0.99
riva
0.98
Act
ivations
Density 0.121%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
