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
    53.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and end-of-sentence indicators

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     recognised
    -0.33
    UpInside
    -0.32
     officially
    -0.32
     nhất
    -0.30
     outlawed
    -0.29
     eksper
    -0.29
     
    -0.29
    officially
    -0.28
    )
    -0.28
     assum
    -0.28
    POSITIVE LOGITS
     betweenstory
    0.71
    ſelf
    0.66
    0.65
     purpoſe
    0.64
    expandindo
    0.63
    <unused14>
    0.61
    <unused28>
    0.61
    <unused43>
    0.61
    <unused52>
    0.61
    <pad>
    0.61
    Act Density 1.863%

    No Known Activations