© 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. 4839
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    68.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specific file formats and data types

    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
     
    -0.40
    DCHECK
    -0.34
    Smarty
    -0.34
    рта
    -0.33
     Improve
    -0.33
    <b>
    -0.32
     swearing
    -0.32
     IMPRO
    -0.31
     firing
    -0.30
    '''
    -0.30
    POSITIVE LOGITS
    TypedDataSet
    0.75
     Administrativna
    0.75
    ########.
    0.69
     estekak
    0.65
    Chham
    0.65
     resourceCulture
    0.61
     autorytatywna
    0.59
    msgTypes
    0.58
    IUrlHelper
    0.57
     snippetHide
    0.57
    Activations Density 0.002%

    No Known Activations