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
    75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    concepts related to abstract qualities and their measurements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    sistors
    -0.56
     himo
    -0.46
    zeera
    -0.46
    thical
    -0.46
    Bons
    -0.45
     autopilot
    -0.45
     pistons
    -0.44
     <>",
    -0.44
    廉
    -0.44
     AssemblyCulture
    -0.44
    POSITIVE LOGITS
    ValueStyle
    0.47
     absence
    0.47
     sœurs
    0.42
     quæ
    0.41
     contextLoads
    0.41
     lleno
    0.40
     llenos
    0.39
    WaitGroup
    0.38
    Olvid
    0.37
     lack
    0.37
    Act Density 0.000%

    No Known Activations