© 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. 15690
    Prev
    Next
    INDEX
    Explanations

    terms associated with cellular or molecular mechanisms in biochemical contexts

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

    connecting words indicating comparisons or relationships such as "too", "or", "is", and "run" when followed by descriptive terms.

    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
    StateException
    -0.41
    KommentareTeilen
    -0.34
    äum
    -0.33
     pama
    -0.33
    構
    -0.33
    idemiology
    -0.32
     confe
    -0.31
     localisation
    -0.31
     Overcome
    -0.31
     समीक्षाओं
    -0.30
    POSITIVE LOGITS
    AnchorStyles
    0.82
    OGND
    0.65
    RectangleBorder
    0.59
    MigrationBuilder
    0.58
    yntaxException
    0.57
    extAlignment
    0.55
     lower
    0.54
     down
    0.53
     الاطلاع
    0.52
    DockStyle
    0.52
    Activations Density 0.614%

    No Known Activations