© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 10282
    Prev
    Next
    INDEX
    Explanations

    important dates and celebrations related to specific cultural or religious festivals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.73
    writeFieldEnd
    -0.56
    BufferException
    -0.55
     Majefty
    -0.54
    ErrUnexpectedEOF
    -0.51
    setVerticalGroup
    -0.51
    ScopeManager
    -0.51
     ब्रेकडाउन
    -0.50
    localctx
    -0.49
    ruptedException
    -0.48
    POSITIVE LOGITS
     calendar
    0.47
     calendars
    0.40
     Calendar
    0.39
     dates
    0.36
     kali
    0.36
    Calendar
    0.35
    calendar
    0.35
    col
    0.35
     voraus
    0.35
     кален
    0.34
    Activations Density 0.099%

    No Known Activations