Neuronpedia
Get Started
API
Releases
Jump To
Search
Models
Assistant Axis
NEW
Circuit Tracer
NEW
Steer
SAE Evals
Exports
Community
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
Attention Out - 16k
0-GEMMASCOPE-ATT-16K
6191
Prev
Next
MODEL
0-gemmascope-att-16k
Source/SAE
INDEX
Go
Explanations
attends to the token "appellant" from various related legal tokens
oai_attention-head · gpt-4o-mini
Triggered by @bot
New Auto-Interp
AutoInterp Type
claude-4-5-haiku
Generate
Top Features by Cosine Similarity
Comparing With
GEMMA-2-2B @ 0-gemmascope-att-16k
Configuration
google/gemma-scope-2b-pt-att/layer_0/width_16k/average_l0_104
How To Load
Prompts (Dashboard)
36,864 prompts, 128 tokens each
Dataset (Dashboard)
monology/pile-uncopyrighted
Features
16,384
Data Type
float32
Hook Name
blocks.0.attn.hook_z
Hook Layer
0
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/0-gemmascope-att-16k/6191?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/0-gemmascope-att-16k/6191?embed=true&embedexplanation=true&embedplots=true&embedsteer=true&embedactivations=true&embedlink=true&embedtest=true
Not in Any Lists
Add to List
▼
No Comments
ADD
Head Attr Weights
0:
0.01
1:
0.02
2:
0.06
3:
0.52
4:
0.07
5:
0.03
6:
0.15
7:
0.09
Negative Logits
↵↵
-0.60
<eos>
-0.59
-0.55
↵
-0.55
,
-0.53
(
-0.50
-
-0.49
-0.49
-0.46
(
-0.44
POSITIVE LOGITS
Efq
0.95
myſelf
0.86
Houſe
0.84
Monfieur
0.84
Jefus
0.83
itſelf
0.82
Anſ
0.82
Theſe
0.81
iſt
0.80
Majefty
0.79
Act
ivations
Density 1.583%
Test
Steer
Stacked
Snippet
Full
Split DFA
Combine DFA
Show Raw Tokens
Show Formatted
Show Breaks
Hide Breaks
No Known Activations