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 - 16k
1-GEMMASCOPE-MLP-16K
8838
Prev
Next
MODEL
1-gemmascope-mlp-16k
Source/SAE
INDEX
Go
Explanations
references to certain types of directed graphs (DCGs)
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 @ 1-gemmascope-mlp-16k
Configuration
google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
How To Load
Prompts (Dashboard)
24,576 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.1.hook_mlp_out
Hook Layer
1
Architecture
jumprelu
Context Size
1,024
Dataset
monology/pile-uncopyrighted
Activation Function
relu
Show All
Embeds
Show Plots
Show Explanation
Show Activations
Show Test Field
Show Steer
Show Link
IFrame
<iframe src="https://www.neuronpedia.org/gemma-2-2b/1-gemmascope-mlp-16k/8838?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true" title="Neuronpedia" style="height: 300px; width: 540px;"></iframe>
Link
https://www.neuronpedia.org/gemma-2-2b/1-gemmascope-mlp-16k/8838?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Negative Logits
DC
-1.72
DC
-1.57
dc
-1.48
dc
-1.31
Dc
-1.20
DCs
-1.10
Dc
-1.02
DCs
-0.88
DM
-0.74
DF
-0.70
POSITIVE LOGITS
OGND
0.82
(!__
0.63
enoord
0.57
gyz
0.55
متعلقه
0.54
Aiheesta
0.54
featureID
0.54
jspx
0.54
صوتيه
0.52
"]
0.51
Act
ivations
Density 0.231%
Test
Steer
Stacked
Snippet
Full
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations
