© 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. 574
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    10
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to the analysis of various scientific methods, particularly in research and statistical contexts

    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
     AssemblyCulture
    -0.48
     بيها
    -0.47
    httphttps
    -0.41
    Rüyada
    -0.40
     åt
    -0.39
    ammans
    -0.38
    yntaxException
    -0.37
     específicamente
    -0.37
    IndentedString
    -0.37
     lisäksi
    -0.36
    POSITIVE LOGITS
     resourceCulture
    0.49
    GEBURTSDATUM
    0.48
    Tikang
    0.43
    PostInfinity
    0.43
     CIO
    0.43
     onPostExecute
    0.42
     Axes
    0.41
     Signal
    0.41
    вро
    0.40
     SSI
    0.40
    Activations Density 1.886%

    No Known Activations