© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7275
    Prev
    Next
    INDEX
    Explanations

    vertical movement or direction-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    directional language describing movement, especially terms like "up", "down", "out", and other spatial relations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.39
     frequency
    -0.36
     format
    -0.34
    </em>
    -0.34
     amely
    -0.34
     id
    -0.33
     (
    -0.33
    .
    -0.32
      
    -0.32
    </u>
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.84
    ########.
    0.81
    évaluateur
    0.74
    bootstrapcdn
    0.73
     CreateTagHelper
    0.73
    ReusableCell
    0.71
    InputBorder
    0.70
    tagHelperRunner
    0.70
    +#+
    0.69
     ब्रेकडाउन
    0.69
    Activations Density 0.120%

    No Known Activations