© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 413
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    82
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    various forms of punctuation and related characters 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
    bootstrapcdn
    -0.52
     ویکی‌پدیای
    -0.51
     Appellee
    -0.48
    ‎‎
    -0.46
    ⎝
    -0.45
    enschein
    -0.45
    Життєпис
    -0.44
     biologic
    -0.44
    Virt
    -0.43
    nomin
    -0.43
    POSITIVE LOGITS
    
    0.47
    #+#
    0.46
    LookAnd
    0.43
     punctuation
    0.43
    +#+#
    0.40
    vivencia
    0.40
    punctuation
    0.39
    วรร
    0.38
    Chham
    0.38
     Taktlose
    0.38
    Activations Density 0.295%

    No Known Activations