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. 1034
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    29.625
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    technical terms and symbols commonly used in code or formal writing, particularly related to web development and mathematics

    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
     Савезне
    -0.40
     ***!
    -0.34
     مشين
    -0.33
     cuarentena
    -0.32
     nawr
    -0.32
     незавершена
    -0.32
    ChildScrollView
    -0.31
     tunt
    -0.30
    getMock
    -0.30
     tatlı
    -0.29
    POSITIVE LOGITS
    rrggbb
    0.66
    
    0.65
     Weiſe
    0.53
    <unused15>
    0.53
     erſten
    0.53
    <unused41>
    0.52
    <unused74>
    0.52
     wiſſen
    0.52
    <pad>
    0.52
    <unused1>
    0.52
    Activations Density 19.055%

    No Known Activations