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. 950
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    77.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    the word "glimmers."

    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
    ticus
    -0.40
    $_['
    -0.39
     Larg
    -0.39
    ⤒
    -0.39
    Personendaten
    -0.38
    URERS
    -0.38
     nieruch
    -0.37
    landais
    -0.37
     nahilalakip
    -0.37
     ویکی‌پدیای
    -0.36
    POSITIVE LOGITS
     snippetHide
    0.59
     CreateTagHelper
    0.57
    RegressionTest
    0.57
     glit
    0.56
     glitter
    0.51
    glit
    0.51
     shimmering
    0.49
    Chham
    0.49
    parsedMessage
    0.47
     shining
    0.47
    Activations Density 0.000%

    No Known Activations