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
    54.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and sentence endings

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    athyroid
    -0.39
     nawr
    -0.37
     brute
    -0.35
     wield
    -0.34
     microfilm
    -0.34
    windowFixed
    -0.34
    rippa
    -0.33
    Geographie
    -0.33
    ndale
    -0.33
    Hauptartikel
    -0.33
    POSITIVE LOGITS
     appropriateness
    0.55
    0.52
    KURZBESCHREIBUNG
    0.49
    ContentAlignment
    0.48
    ContextHolder
    0.48
    InstrumentedTest
    0.48
    transQ
    0.47
     verhe
    0.46
    SystemColors
    0.45
    +#+#
    0.45
    Act Density 2.212%

    No Known Activations