© 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. 4873
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    57.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    various forms of punctuation and symbols 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
     hipó
    -0.41
    Literatur
    -0.31
    Seznam
    -0.28
     ilman
    -0.28
     frein
    -0.27
     Grundlage
    -0.27
    )}=
    -0.27
    =.
    -0.26
     Ανακτήθηκε
    -0.26
     Schuster
    -0.26
    POSITIVE LOGITS
     kasarigan
    0.74
     ExecuteAsync
    0.72
    
    0.71
     '\\;'
    0.69
    MigrationBuilder
    0.66
    IntoConstraints
    0.65
    rrggbb
    0.63
     noDo
    0.62
    Хьажоргаш
    0.61
    ViewInit
    0.59
    Activations Density 1.635%

    No Known Activations