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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 2737
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    53.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation and special characters, indicating potential pauses or shifts in the 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
     nawr
    -0.40
    茁
    -0.35
    ndale
    -0.35
     vigour
    -0.35
     adulte
    -0.34
     Familienname
    -0.34
    ondale
    -0.33
    tagext
    -0.33
    Diwedd
    -0.32
    >\
    -0.32
    POSITIVE LOGITS
    transQ
    0.57
     onely
    0.57
     Only
    0.54
     only
    0.54
    only
    0.53
     ONLY
    0.53
    LEGGI
    0.52
    évaluateur
    0.51
    
    0.51
     kasarigan
    0.50
    Activations Density 1.729%

    No Known Activations