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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 1250
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    66
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to crime and illegal actions

    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
    -0.59
     Audiodateien
    -0.47
    zheimer
    -0.47
     heilig
    -0.46
    estacks
    -0.45
    󠁣
    -0.45
    rometry
    -0.44
     compressed
    -0.44
    compressed
    -0.43
    sistors
    -0.43
    POSITIVE LOGITS
     crime
    0.59
    crime
    0.48
     CRIME
    0.48
     Crime
    0.46
     crimes
    0.44
    Crime
    0.41
    ActivityCompat
    0.40
    Activités
    0.40
     actividad
    0.38
    犯罪
    0.38
    Activations Density 0.029%

    No Known Activations