© 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
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 5734
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    48.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    mathematical equations and formulations

    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
    UpInside
    -0.35
     couvercle
    -0.35
     presidencia
    -0.34
     olds
    -0.33
    󠁣
    -0.33
     cucchiaio
    -0.32
     ब्रेकडाउन
    -0.32
    newArrayList
    -0.32
    DCHECK
    -0.31
     doigt
    -0.31
    POSITIVE LOGITS
    LookAnd
    0.77
    setVerticalGroup
    0.65
     CreateTagHelper
    0.65
     kasarigan
    0.64
     '\\;'
    0.64
    esModule
    0.59
    InstrumentedTest
    0.57
     contextLoads
    0.54
     dAtA
    0.52
    bcryptjs
    0.52
    Activations Density 1.956%

    No Known Activations