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
    54
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks, particularly focusing on sentence terminators and structural indicators in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     nawr
    -0.35
    Hauptartikel
    -0.33
    RTEE
    -0.31
     hypo
    -0.31
     frein
    -0.31
     adulte
    -0.31
    switchTo
    -0.30
     recognised
    -0.30
    Geographie
    -0.30
    isième
    -0.29
    POSITIVE LOGITS
     purpoſe
    0.68
    ſelf
    0.68
     ſta
    0.61
     AssemblyCompany
    0.60
     queſta
    0.60
     ſtand
    0.60
     Verſ
    0.59
     Chriſt
    0.58
    ientras
    0.57
    majánló
    0.57
    Act Density 1.203%

    No Known Activations