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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 854
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    83
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    various types of punctuation and symbols, including specific formatting characters

    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
    XtraGrid
    -0.47
    arangay
    -0.46
    :✨
    -0.45
    󠁮
    -0.44
     Antibody
    -0.44
     Greens
    -0.43
     Appellee
    -0.43
    nomin
    -0.43
    Virt
    -0.42
    winder
    -0.42
    POSITIVE LOGITS
     Administrativna
    0.47
     punctuation
    0.43
    +#+#
    0.41
    PerformLayout
    0.39
    vivencia
    0.39
    gestaltung
    0.38
    ymce
    0.37
    Билгалдахарш
    0.37
     characters
    0.36
    ctuation
    0.36
    Activations Density 0.339%

    No Known Activations