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
4-GEMMASCOPE-MLP-65K
10
Prev
Next
MODEL
4-gemmascope-mlp-65k
Source/SAE
INDEX
Go
Explanations
numerical sequences and punctuation related to dates and identification
oai_token-act-pair · gpt-4o-mini
Triggered by @bot
No Scores
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 4-gemmascope-mlp-65k
Configuration
google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
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.4.hook_mlp_out
Hook Layer
4
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/4-gemmascope-mlp-65k/10?embed=true&embedexplanation=true&embedplots=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/4-gemmascope-mlp-65k/10?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
-0.58
Leg
-0.51
lucene
-0.50
ment
-0.50
leg
-0.49
sole
-0.47
co
-0.47
terça
-0.46
be
-0.44
deps
-0.43
POSITIVE LOGITS
born
1.19
Born
1.13
BORN
1.12
birth
1.08
Born
1.02
مواليد
1.01
born
1.00
Birth
0.99
birth
0.97
Birth
0.96
Act
ivations
Density 0.167%
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
