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. 2712
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    61.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    mentions of authors, books, and discussions related to literature or scholarly works

    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
    WriteTagHelper
    -0.61
     Wiktionnaire
    -0.60
     AssemblyCulture
    -0.60
    andExpect
    -0.57
    :✨
    -0.57
    tanleria
    -0.57
    Jeografia
    -0.57
    aarrggbb
    -0.56
    httphttps
    -0.56
    AsNil
    -0.56
    POSITIVE LOGITS
     membahas
    0.35
     köny
    0.35
     authored
    0.34
     book
    0.33
    going
    0.33
     themed
    0.33
     referenced
    0.33
     titled
    0.32
     portray
    0.32
    텐츠
    0.32
    Activations Density 0.205%

    No Known Activations