© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4087
    Prev
    Next
    INDEX
    Explanations

    concepts related to historical political conflicts and leadership

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

    Followed by names or titles

    np_acts-logits-general · gemini-2.0-flash

    historical figures and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     carport
    -0.65
     Gallimard
    -0.64
     ২০১
    -0.61
     Freeway
    -0.59
     helicopters
    -0.59
     ویکی‌پدیا
    -0.58
     garage
    -0.57
     Airport
    -0.57
    aéroport
    -0.56
     Airports
    -0.56
    POSITIVE LOGITS
     steamboat
    0.65
     slave
    0.62
     Мексичка
    0.60
     steam
    0.58
    olera
    0.57
    CPtr
    0.57
     Steam
    0.57
     Ottoman
    0.56
    DockStyle
    0.55
     slaves
    0.55
    Activations Density 1.457%

    No Known Activations