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
    53
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuations and symbols that characterize dialogue or pause in writing

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    DCHECK
    -0.41
     nawr
    -0.38
     basin
    -0.35
    Transpose
    -0.35
     termo
    -0.34
     recognise
    -0.33
    ropoda
    -0.33
    busters
    -0.32
    basin
    -0.32
    lastonbury
    -0.32
    POSITIVE LOGITS
    ########.
    0.59
    ContentAlignment
    0.56
    PullParser
    0.56
    IntoConstraints
    0.54
     '\\;'
    0.54
    setVerticalGroup
    0.53
    تقاوى
    0.53
     ExecuteAsync
    0.52
     noDo
    0.52
    ViewInit
    0.52
    Act Density 0.939%

    No Known Activations