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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 4038
    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
     Statistic
    -0.47
     blacklist
    -0.47
    doria
    -0.47
    WriteTagHelper
    -0.46
    GEBURTSDATUM
    -0.46
    :✨
    -0.45
    ikusbot
    -0.45
    apimachinery
    -0.45
     Statistics
    -0.44
    Recovered
    -0.44
    POSITIVE LOGITS
     conversation
    0.74
     conversations
    0.73
     discussions
    0.65
     dialogue
    0.63
     conversación
    0.60
     discussion
    0.56
     dialog
    0.54
    conversations
    0.53
    Conversations
    0.52
     talk
    0.52
    Activations Density 0.000%

    No Known Activations