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. 956
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    67.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    emotions and complexities within relationships

    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
     ویکی‌پدیای
    -0.59
    Hentet
    -0.59
    tyimages
    -0.55
    bootstrapcdn
    -0.55
    estacks
    -0.55
     Audiodateien
    -0.51
    ロウィン
    -0.51
    Parcelize
    -0.51
     AssemblyCompany
    -0.51
     ویکی‌پدیا
    -0.51
    POSITIVE LOGITS
     choices
    0.42
     decisions
    0.42
     decisiones
    0.40
    choices
    0.38
     emotionally
    0.37
     feelings
    0.37
     moments
    0.37
    fromnode
    0.36
     decision
    0.35
     når
    0.35
    Activations Density 0.004%

    No Known Activations