© 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. 1286
    Prev
    Next
    INDEX
    Explanations

    terms related to crime statistics and public safety

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

    Incidents, deaths, cases, and occurrences

    np_acts-logits-general · gemini-2.0-flash

    incidents and deaths

    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
    ніципалі
    -0.46
     الحره
    -0.41
    NameInMap
    -0.41
    رشف
    -0.40
     schoenen
    -0.40
    ędziesz
    -0.39
    XmlAccessorType
    -0.39
    sprüng
    -0.38
     تک
    -0.38
    chappen
    -0.35
    POSITIVE LOGITS
     incidents
    0.81
     victims
    0.68
     deaths
    0.65
     occurrences
    0.65
     incident
    0.65
     Incidents
    0.62
     victim
    0.62
     violence
    0.60
    Violence
    0.57
     killings
    0.56
    Activations Density 0.304%

    No Known Activations