© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 4606
    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

    terms related to files and data processing

    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
     largely
    -0.38
     
    -0.36
     principally
    -0.35
    |}
    -0.34
    ruik
    -0.33
     Larg
    -0.33
    ==========
    -0.32
    pośred
    -0.31
     famous
    -0.31
    HttpFoundation
    -0.31
    POSITIVE LOGITS
    #+#
    0.60
    TypedDataSet
    0.58
     Administrativna
    0.57
    RenderAtEndOf
    0.56
    Хьажоргаш
    0.55
    ValueStyle
    0.55
    XmlAccessType
    0.55
     للاسماء
    0.54
     resourceCulture
    0.53
    fromnode
    0.53
    Activations Density 0.057%

    No Known Activations