© 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. 3153
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    71.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    elements of HTML or markup syntax

    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
    ]},
    -0.34
    AndroidJUnit
    -0.32
    GeneratedMessage
    -0.31
    ]',
    -0.30
     }},
    -0.30
    MessageOf
    -0.29
    RTHOOK
    -0.29
    ViewImports
    -0.29
    ]),
    -0.28
    WriteBarrier
    -0.28
    POSITIVE LOGITS
     Choices
    0.73
    aarrggbb
    0.71
     للمعارف
    0.65
    Choices
    0.65
     choices
    0.64
     Options
    0.58
    choices
    0.56
     lenker
    0.56
     beſch
    0.56
    /**
    0.56
    Activations Density 4.633%

    No Known Activations