© 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. 4477
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    47.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    programming-related functions and return statements

    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
     Italijanski
    -0.60
    WriteTagHelper
    -0.58
    Diweddarwch
    -0.47
     linkovi
    -0.45
     Italij
    -0.44
     někdo
    -0.44
    GTCX
    -0.43
     HasFactory
    -0.42
     kwiaty
    -0.42
    Personendaten
    -0.42
    POSITIVE LOGITS
    cupa
    0.47
    def
    0.42
     Fe
    0.41
     сім
    0.41
     Qui
    0.41
    useEffect
    0.41
    WithIOException
    0.41
     Lid
    0.40
     return
    0.40
    synthesize
    0.40
    Activations Density 0.102%

    No Known Activations