© 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. 570
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    66.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    mathematical terms and symbols, particularly those related to equations and formulas

    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
    doria
    -0.50
    GEBURTS
    -0.50
    UpInside
    -0.50
    httphttps
    -0.49
    styleType
    -0.48
    OGND
    -0.46
    andExpect
    -0.46
     وتسجيلات
    -0.46
    ⎨
    -0.46
    WriteTagHelper
    -0.45
    POSITIVE LOGITS
    Билгалдахарш
    0.49
     CreateTagHelper
    0.44
     symbols
    0.43
    MethodImpl
    0.37
    ValueStyle
    0.36
    centralwidget
    0.36
     symbol
    0.36
     equation
    0.34
    Хьажоргаш
    0.34
     space
    0.34
    Activations Density 0.175%

    No Known Activations