© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13872
    Prev
    Next
    INDEX
    Explanations

    topics related to obituaries and death notices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "memorial" or beginning of turn

    np_acts-logits-general · gemini-2.0-flash

    memorial societies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    Чыганаклар
    -0.35
     estrategias
    -0.34
    ありがとうございます
    -0.34
    ื่น
    -0.33
    emples
    -0.33
     estrategia
    -0.32
     aank
    -0.32
     ansiedad
    -0.32
    ปก
    -0.30
    ChildScrollView
    -0.30
    POSITIVE LOGITS
     mourned
    0.63
    LogFactory
    0.57
    Tributes
    0.56
     necro
    0.56
     funeral
    0.56
     محفوظة
    0.56
     resultCode
    0.54
     Infórmanos
    0.54
    Décès
    0.53
     obituary
    0.51
    Activations Density 0.078%

    No Known Activations