Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 277
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    44.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    code formatting and structural elements in programming or markup languages

    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
    tagext
    -0.36
     
    -0.33
    मति
    -0.29
     caminando
    -0.28
     fazenda
    -0.28
     d
    -0.28
     wirklich
    -0.28
    ]
    -0.28
     \
    -0.28
    AddTagHelper
    -0.28
    POSITIVE LOGITS
     Administrativna
    0.76
     UTF
    0.69
    bibfield
    0.66
    rrggbb
    0.65
    Tikang
    0.64
     EnglishChoose
    0.63
    ंदीखरीदारी
    0.59
     utf
    0.58
    텐츠
    0.57
    UTF
    0.57
    Activations Density 1.869%

    No Known Activations