© 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. 4609
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    60.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation and formatting-related terms 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
     terme
    -0.38
    ).__
    -0.38
     hoga
    -0.37
    ‎‎
    -0.36
    Truthy
    -0.35
    Literatur
    -0.35
     Ανακτήθηκε
    -0.35
    enschein
    -0.34
    foobar
    -0.34
    Seznam
    -0.34
    POSITIVE LOGITS
    +#+#
    0.65
     Administrativna
    0.57
    ########.
    0.54
     propOrder
    0.54
    Хьажоргаш
    0.52
    setVerticalGroup
    0.52
     Taktlose
    0.50
     saurait
    0.49
    ſelf
    0.48
     שוליים
    0.48
    Activations Density 4.929%

    No Known Activations