© 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. 1556
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    59.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    function and type definitions in programming code

    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
    -0.47
    Aholisi
    -0.46
    Vidite
    -0.46
    Hochspringen
    -0.45
    ViewImports
    -0.44
     Italijanski
    -0.44
    IsContent
    -0.43
     InputDecoration
    -0.40
     nawr
    -0.40
     تعدى
    -0.40
    POSITIVE LOGITS
    propTypes
    0.50
     propTypes
    0.49
    ;++
    0.43
    SafeAreaView
    0.43
    NullException
    0.42
     FIA
    0.41
    Искәрмәләр
    0.41
     Normdatei
    0.40
    исленность
    0.40
    čin
    0.40
    Activations Density 0.003%

    No Known Activations