© 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. 15001
    Prev
    Next
    INDEX
    Explanations

    references to death or dying incidents

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

    death or dying

    np_acts-logits-general · gemini-2.0-flash

    dying or being killed

    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
     EconPapers
    -1.05
     للاسماء
    -0.72
    WithMany
    -0.71
     invokingState
    -0.69
    出版年
    -0.69
    ագրություններ
    -0.69
    AccessorTable
    -0.65
    WebServlet
    -0.64
     OFDb
    -0.63
     ModelExpression
    -0.63
    POSITIVE LOGITS
     tragically
    0.74
     due
    0.68
     mysteriously
    0.68
     trying
    0.61
     accidente
    0.61
     tragic
    0.61
     unfortunate
    0.59
     Trag
    0.58
     preventable
    0.58
     attempting
    0.57
    Activations Density 0.285%

    No Known Activations