© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10477
    Prev
    Next
    INDEX
    Explanations

    this neuron detects references to irish history (place names, people, battles.)

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     ProtoMessage
    -0.59
     TextAppearance
    -0.56
     JpaRepository
    -0.56
    AsUp
    -0.50
    CreateMap
    -0.49
    initComponents
    -0.49
    BASEPATH
    -0.48
    etCode
    -0.48
    upuesto
    -0.47
     Cleaners
    -0.47
    POSITIVE LOGITS
     Sin
    0.72
    الحياه
    0.66
     Dec
    0.63
    Sin
    0.62
     Ni
    0.60
    tuig
    0.59
     Ao
    0.57
     ویکی‌آمباردا
    0.56
     Eo
    0.56
     Ci
    0.55
    Activations Density 0.979%

    No Known Activations