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. 5237
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    44.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    complex mathematical expressions and notations

    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
    揄
    -0.32
     off
    -0.32
    ielt
    -0.27
    Incorrect
    -0.27
    off
    -0.26
     Wiel
    -0.25
     hipó
    -0.25
    DoubleClick
    -0.25
     Hipp
    -0.25
     Toen
    -0.24
    POSITIVE LOGITS
     queſta
    0.88
    setVerticalGroup
    0.72
    LookAnd
    0.72
    IntoConstraints
    0.68
    <unused74>
    0.67
     laſſen
    0.67
    [@BOS@]
    0.66
    <unused14>
    0.66
    <unused23>
    0.66
    <unused28>
    0.66
    Activations Density 2.643%

    No Known Activations