© 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. 15-GEMMASCOPE-RES-16K
    11. 9342
    Prev
    Next
    INDEX
    Explanations

    incidents of violence and significant accidents, particularly those involving casualties or injuries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Works
    -0.45
     works
    -0.43
     Pursu
    -0.41
     adap
    -0.41
    скоп
    -0.41
    iveau
    -0.40
     programmes
    -0.40
     programa
    -0.40
    DoubleQuotes
    -0.40
    titur
    -0.40
    POSITIVE LOGITS
     occurred
    1.09
     happened
    1.07
     occured
    1.01
     occurring
    0.95
     happening
    0.95
     occurrence
    0.93
    happened
    0.92
     ocurrido
    0.92
     incidence
    0.91
     incident
    0.89
    Activations Density 0.584%

    No Known Activations