© 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. 4624
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    42.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    ellipsis or sections signaling omissions in text

    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
     leña
    -0.31
     
    -0.31
    -
    -0.30
    )
    -0.29
    <eos>
    -0.29
    ers
    -0.28
     foot
    -0.28
    ns
    -0.27
     off
    -0.27
    .
    -0.27
    POSITIVE LOGITS
    setVerticalGroup
    0.98
    +#+
    0.83
     purpoſe
    0.78
     Monfieur
    0.78
    ſelf
    0.77
     propOrder
    0.77
     nakalista
    0.75
    <pad>
    0.75
    <unused1>
    0.74
    <unused14>
    0.74
    Activations Density 0.219%

    No Known Activations