Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Slack
Blog
Privacy & Terms
Contact
Sign In
© Neuronpedia 2025
Privacy & Terms
Blog
GitHub
Slack
Twitter
Contact
Home
Google DeepMind · Exploring Gemma 2 with Gemma Scope
Gemma-2-2B
MLP Out - 65k
0-GEMMASCOPE-MLP-65K
60966
Prev
Next
MODEL
0-gemmascope-mlp-65k
Source/SAE
INDEX
Go
Explanations
quoted terms related to different medical conditions
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-3-5-haiku-20241022
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 0-gemmascope-mlp-65k
Configuration
google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
65,536
Data Type
float32
Hook Name
blocks.0.hook_mlp_out
Hook Layer
0
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Plots
Explanation
Show Test Field
Default Test Text
IFrame
<iframe src=https://www.neuronpedia.org/gemma-2-2b/0-gemmascope-mlp-65k/60966?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/0-gemmascope-mlp-65k/60966?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
'
-3.05
‘
-2.55
‚
-1.83
('
-1.82
『
-1.81
-'
-1.73
(‘
-1.70
{'
-1.59
['
-1.57
'-
-1.56
POSITIVE LOGITS
“
0.88
“
0.81
{"
0.69
(“
0.69
<h4>
0.68
—“
0.68
“[
0.68
("
0.68
ModelExpression
0.66
，“
0.65
Act
ivations
Density 0.139%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
