Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    53.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    elements indicating lists, sequences, or items of discussion in a text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    httphttps
    -0.35
    hooks
    -0.35
     referenties
    -0.32
    letzt
    -0.32
     recognised
    -0.32
    UGAL
    -0.31
     reforma
    -0.31
     orthodox
    -0.30
     req
    -0.30
    cloak
    -0.30
    POSITIVE LOGITS
     betweenstory
    0.68
    transQ
    0.58
    ChildScrollView
    0.57
    LookAnd
    0.56
    ValueStyle
    0.55
     purpoſe
    0.55
     propOrder
    0.55
    Plenty
    0.54
    ſelf
    0.54
    expandindo
    0.54
    Act Density 0.668%

    No Known Activations