© 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. 2882
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    65
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to processes or timelines, particularly in a developmental or analytical context

    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
    :✨
    -0.57
     AssemblyCulture
    -0.57
     TextAppearance
    -0.57
     himo
    -0.56
    httphttps
    -0.56
    $_['
    -0.54
     neutrons
    -0.53
     Audiodateien
    -0.52
     وتسجيلات
    -0.52
     immunos
    -0.51
    POSITIVE LOGITS
     stages
    0.65
     etapa
    0.64
     etapas
    0.63
     étapes
    0.61
     étape
    0.59
     stage
    0.58
     progression
    0.56
     phase
    0.55
     Phase
    0.54
     progressing
    0.53
    Activations Density 0.003%

    No Known Activations