© 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. 5648
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    32.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    names and attributes related to programming elements and data structures

    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
     kaarangay
    -0.64
    GIVEREF
    -0.58
     незавершена
    -0.56
    MENAFN
    -0.55
     himo
    -0.51
    日閲覧
    -0.50
     intptr
    -0.48
    RTSC
    -0.47
     klar
    -0.47
    WriteTagHelper
    -0.47
    POSITIVE LOGITS
    tagHelper
    0.43
     createSlice
    0.41
    getExternal
    0.41
    NOPQRST
    0.40
    XmlEnum
    0.39
     obligé
    0.39
     geluid
    0.37
    Története
    0.36
    JvmStatic
    0.36
     propOrder
    0.36
    Activations Density 0.085%

    No Known Activations