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. 1352
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    71.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    referring to protective equipment or devices

    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
    Personendaten
    -0.60
     Audiodateien
    -0.57
    zheimer
    -0.53
    GEBURTSDATUM
    -0.53
     Probable
    -0.51
    httphttps
    -0.50
    HttpFoundation
    -0.50
    pexpr
    -0.49
    deus
    -0.48
    SequentialGroup
    -0.48
    POSITIVE LOGITS
     protective
    0.63
    protective
    0.54
     protection
    0.51
     PROTECT
    0.49
     Protective
    0.49
     protección
    0.48
     pelindung
    0.48
    styleUrls
    0.48
     safety
    0.47
     attire
    0.46
    Activations Density 0.000%

    No Known Activations