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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 745
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    72
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specific nouns related to personal spaces or rooms

    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
    Personendaten
    -0.52
    anguera
    -0.47
    bewerken
    -0.44
    tyimages
    -0.44
    ikusbot
    -0.44
    WriteTagHelper
    -0.44
    pexpr
    -0.44
     ролях
    -0.44
    apimachinery
    -0.43
    المناصب
    -0.43
    POSITIVE LOGITS
     bedroom
    0.69
    bedroom
    0.55
     bedrooms
    0.54
     Bedroom
    0.54
    Bedroom
    0.51
     dormitorio
    0.46
     BEDROOM
    0.46
    room
    0.44
     room
    0.44
     rooms
    0.40
    Activations Density 0.000%

    No Known Activations