© 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. 565
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    49.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation and structural elements in text

    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
    tanleria
    -0.42
     Audiodateien
    -0.36
    äsident
    -0.35
    isième
    -0.35
    WriteTagHelper
    -0.35
    Incorrect
    -0.33
    czny
    -0.32
     adulte
    -0.32
    ėte
    -0.31
    Eksteraj
    -0.31
    POSITIVE LOGITS
    setVerticalGroup
    0.67
    LookAnd
    0.60
     queſta
    0.54
     defaultstate
    0.46
     noDo
    0.44
     câte
    0.44
     ſind
    0.43
     geſ
    0.43
    PerformLayout
    0.42
    +");
    0.42
    Activations Density 4.201%

    No Known Activations