© 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
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 4777
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    77.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to balance and weight concepts

    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
    Personendaten
    -0.59
     Paglinawan
    -0.57
    doria
    -0.54
    !*\
    -0.50
     commonest
    -0.50
    ⎨
    -0.49
    djangoproject
    -0.48
    GEBURTSDATUM
    -0.48
     Audiodateien
    -0.48
     esternos
    -0.47
    POSITIVE LOGITS
     weight
    0.62
    weight
    0.53
     weigh
    0.48
     Weight
    0.47
    weigh
    0.46
     weighing
    0.45
    WEIGHT
    0.45
    gewicht
    0.43
    WaitGroup
    0.43
     load
    0.43
    Activations Density 0.001%

    No Known Activations