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
    37.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    significant punctuation and formatting elements in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    WireFormat
    -0.36
     peringatan
    -0.36
     Landwir
    -0.35
     dapur
    -0.34
     nawr
    -0.33
     humild
    -0.33
     Messung
    -0.33
     pungkas
    -0.33
     recuperação
    -0.33
    Legături
    -0.33
    POSITIVE LOGITS
    rrggbb
    0.77
    setVerticalGroup
    0.69
    transQ
    0.68
     betweenstory
    0.68
     propOrder
    0.65
    0.58
    Hoc
    0.55
     queſta
    0.54
     Hoc
    0.53
    bibfield
    0.53
    Act Density 4.235%

    No Known Activations