Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 42
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    55.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation and sentence-ending symbols to assess the flow of text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    pyvene/gemma-reft-r1-9b-it-res/l20
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.52
    tagext
    -0.47
     nawr
    -0.42
    Geographie
    -0.41
    Smarty
    -0.41
    wayat
    -0.40
     wiedzy
    -0.40
    HomeAsUp
    -0.39
     correctes
    -0.39
    CORRECT
    -0.39
    POSITIVE LOGITS
    LookAnd
    0.56
    LEGGI
    0.50
    fromnode
    0.49
    Manbalar
    0.42
     betweenstory
    0.41
    /*
    0.39
    Rüyada
    0.39
     purpoſe
    0.39
    AccessorTable
    0.39
     resourceCulture
    0.38
    Activations Density 2.646%

    No Known Activations