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. 2684
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    50.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    numerical values and statistical data

    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
    :✨
    -0.59
    〗
    -0.53
    SequentialGroup
    -0.52
     lenker
    -0.51
     jScrollPane
    -0.51
    Бахар
    -0.49
    ➟
    -0.49
    </caption>
    -0.48
    RenderAtEndOf
    -0.46
    المناصب
    -0.46
    POSITIVE LOGITS
    Insee
    0.37
     للاسماء
    0.37
     nodes
    0.35
    Fuck
    0.35
     contextLoads
    0.34
     pairs
    0.34
    ượu
    0.33
     HttpNotFound
    0.33
    itrile
    0.33
     Monate
    0.32
    Activations Density 0.001%

    No Known Activations