© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 125
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    62.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases related to frameworks or models in theoretical discussions

    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
    WriteTagHelper
    -0.52
     esternos
    -0.49
     thankfully
    -0.46
     Schild
    -0.46
    $_['
    -0.45
     nggak
    -0.43
     horribly
    -0.43
    󠁣
    -0.43
     bluetooth
    -0.42
     nerfed
    -0.42
    POSITIVE LOGITS
    PreExecute
    0.62
    basicConfig
    0.48
    contentLoaded
    0.47
     Normdatei
    0.47
     framework
    0.46
     plan
    0.44
    modelBuilder
    0.44
     structure
    0.44
     unknownFields
    0.43
    Edm
    0.43
    Activations Density 0.000%

    No Known Activations