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
    41.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    patterns in code structure or syntax

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    rom
    -0.38
    -
    -0.38
    wood
    -0.37
    )
    -0.33
    ne
    -0.33
     of
    -0.31
    ↵
    -0.31
     
    -0.31
    or
    -0.30
     einzu
    -0.30
    POSITIVE LOGITS
     betweenstory
    0.82
    0.81
    <unused1>
    0.79
    <unused3>
    0.79
    <unused21>
    0.79
    <unused14>
    0.79
    <unused43>
    0.79
    <unused51>
    0.79
    <unused74>
    0.79
    <unused79>
    0.79
    Act Density 1.706%

    No Known Activations