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
61029
Prev
Next
MODEL
0-gemmascope-mlp-65k
Source/SAE
INDEX
Go
Explanations
the conjunction "y" indicating connections or additions in a sequence
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/61029?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/61029?embed=true&embedexplanation=true&embedplots=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
y
-2.30
Y
-1.74
y
-1.61
Y
-1.36
ｙ
-1.05
getY
-0.90
ʏ
-0.89
𝑦
-0.88
𝘆
-0.87
yo
-0.87
POSITIVE LOGITS
and
1.06
$\&$
0.95
\&
0.90
và
0.88
และ
0.85
незавершена
0.83
WebElementEntity
0.82
And
0.81
and
0.81
And
0.81
Act
ivations
Density 0.041%
Stacked
Snippet
Full
Show Breaks
Hide Breaks
No Known Activations
