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
    50.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation and sentence boundaries, focusing on how sentences are structured

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.43
     nawr
    -0.41
     Wikimedijinoj
    -0.40
    Geographie
    -0.37
     theoretical
    -0.37
     nematode
    -0.37
     powder
    -0.36
     hydraulic
    -0.36
    DCHECK
    -0.36
    reszcie
    -0.36
    POSITIVE LOGITS
    ंदीखरीदारी
    0.57
     betweenstory
    0.55
    InstrumentedTest
    0.52
    setVerticalGroup
    0.51
    WaitGroup
    0.50
     kasarigan
    0.47
    fromnode
    0.47
    
    0.45
    ViewInit
    0.44
     Zeitraum
    0.44
    Act Density 1.451%

    No Known Activations