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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 10366
    Prev
    Next
    INDEX
    Explanations

    mentions of ethnic groups and killings in Croatia and Bosnia

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     فريبيس
    -0.60
     חיצוניים
    -0.57
    setVerticalGroup
    -0.57
    aarrggbb
    -0.56
    PMailer
    -0.56
    醐
    -0.56
    ISupport
    -0.56
    AnchorStyles
    -0.55
    tify
    -0.55
     Serve
    -0.55
    POSITIVE LOGITS
     otomatig
    0.47
    EnumMember
    0.46
    voort
    0.46
    PreInfinity
    0.44
    wenye
    0.43
    SpringBoot
    0.43
    下载附件
    0.43
    contentLoaded
    0.42
     etmeye
    0.42
    uluk
    0.41
    Activations Density 2.708%

    No Known Activations