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
    55.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    questions and interrogative statements in the text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     traditionally
    -0.37
     nawr
    -0.37
     recognised
    -0.35
     Traditionally
    -0.35
     expert
    -0.34
    newArrayList
    -0.32
     prevailing
    -0.32
    off
    -0.31
    isième
    -0.30
    DCHECK
    -0.30
    POSITIVE LOGITS
     purpoſe
    0.73
    ſelf
    0.72
     raiſ
    0.70
    ſelves
    0.68
     defaultstate
    0.60
    InstrumentedTest
    0.60
     itſelf
    0.60
     ſtand
    0.59
     queſta
    0.59
     myſelf
    0.59
    Act Density 1.385%

    No Known Activations