© 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. 3126
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    64.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    Python class definitions and their constructors

    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
     Stoppers
    -0.44
     Reverso
    -0.43
    tonode
    -0.42
     typelib
    -0.42
     getIndex
    -0.41
    Hochspringen
    -0.41
    -------------</
    -0.39
    </>
    -0.39
     estekak
    -0.38
    ReadKey
    -0.38
    POSITIVE LOGITS
    WithIOException
    0.57
    XmlAccessorType
    0.55
    AutoField
    0.51
     StatefulWidget
    0.47
    disposing
    0.47
    StoryboardSegue
    0.46
    FormBuilder
    0.46
     Initialize
    0.43
    class
    0.42
    Initialize
    0.42
    Activations Density 0.282%

    No Known Activations