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. 5277
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    0
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations
    No Explanations Found
    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
     ModelExpression
    -0.81
     EconPapers
    -0.64
    DockStyle
    -0.55
     CFC
    -0.55
    WriteTagHelper
    -0.55
    Hochspringen
    -0.51
     ProtoMessage
    -0.51
    〗
    -0.50
    grandfather
    -0.50
    youts
    -0.50
    POSITIVE LOGITS
    éndolo
    0.34
    而非
    0.33
     although
    0.32
     gång
    0.31
    íté
    0.31
    Viki
    0.31
     кӀ
    0.30
     rather
    0.29
    Insee
    0.29
     Vielzahl
    0.29
    Activations Density 0.000%

    No Known Activations