© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 897
    Prev
    Next
    INDEX
    Explanations

    references to crime scenes and incidents related to legal processes

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

    "The" followed by "scene"

    np_acts-logits-general · gemini-2.0-flash

    crime scene or site

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     estekak
    -0.92
     defaultstate
    -0.87
    MemoryWarning
    -0.85
    MigrationBuilder
    -0.85
     незавершена
    -0.85
     nahilalakip
    -0.85
     getopt
    -0.83
    HtmlAttribute
    -0.83
    migrationBuilder
    -0.82
    Personensuche
    -0.82
    POSITIVE LOGITS
     site
    1.95
     scene
    1.73
    site
    1.54
     Site
    1.45
    Site
    1.44
    scene
    1.41
     sites
    1.39
    SITE
    1.26
     SITE
    1.25
    现场
    1.18
    Activations Density 0.261%

    No Known Activations