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. 2693
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    63
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    assertions or claims made by experts and analysts

    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
     AssemblyCulture
    -0.60
    parsedMessage
    -0.60
    chemise
    -0.57
     surla
    -0.55
    AnimationsModule
    -0.54
    Diweddarwch
    -0.54
     nitrous
    -0.54
    нгред
    -0.53
     &___
    -0.52
     ་་
    -0.52
    POSITIVE LOGITS
    ValueStyle
    0.40
     said
    0.40
     afir
    0.40
    klaim
    0.38
     saying
    0.37
     asserted
    0.36
     claimed
    0.35
     afirmar
    0.34
     CLAIM
    0.34
     told
    0.33
    Activations Density 0.003%

    No Known Activations