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-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14428
    Prev
    Next
    INDEX
    Explanations

    words and phrases broadly related to violence, especially those involving police, attacks, and death, as well as legal proceedings.

    oai_token-act-pair · gemini-2.0-flash

    Crime and violence

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    رشف
    -0.65
     typelib
    -0.64
    rungsseite
    -0.64
     utafitiHapana
    -0.63
    .*")]
    -0.62
     Catawiki
    -0.59
    MessageOf
    -0.59
     CURIAM
    -0.58
     متعلقه
    -0.58
     समीक्षाओं
    -0.57
    POSITIVE LOGITS
     double
    0.48
     early
    0.43
     ?>">
    0.41
    υν
    0.41
    unhofer
    0.40
     breakout
    0.40
    slee
    0.40
     fatal
    0.40
    double
    0.39
    ToAction
    0.39
    Activations Density 1.689%

    No Known Activations