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. 1175
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    40
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation and characters that separate sections of 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
     condena
    -0.32
     legais
    -0.31
     miteinander
    -0.30
    éez
    -0.28
     arbejds
    -0.28
     świ
    -0.27
     '
    -0.25
     
    -0.25
    ))+
    -0.25
     sustitu
    -0.25
    POSITIVE LOGITS
     betweenstory
    0.65
    MigrationBuilder
    0.60
     nakalista
    0.59
    بوابة
    0.59
    setVerticalGroup
    0.59
     ſehen
    0.57
    ftance
    0.57
     NSCoder
    0.57
    
    0.56
    <unused1>
    0.56
    Activations Density 3.742%

    No Known Activations