© 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. 14552
    Prev
    Next
    INDEX
    Explanations

    statistical terms and numeric data related to scientific studies

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

    numeric values in tables and statistical data presentations.

    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
     informée
    -0.80
    rungsseite
    -0.77
    AndEndTag
    -0.74
    OGND
    -0.72
     fubject
    -0.72
    parsedMessage
    -0.71
    ロウィン
    -0.71
    iſchen
    -0.69
     snippetHide
    -0.69
     Administrativna
    -0.68
    POSITIVE LOGITS
     فريبيس
    0.40
     
    0.38
     mean
    0.34
     values
    0.33
     size
    0.33
     expected
    0.33
     raw
    0.32
     trio
    0.31
     لن
    0.31
     gu
    0.30
    Activations Density 0.242%

    No Known Activations