© 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. 21-GEMMASCOPE-RES-16K
    11. 1568
    Prev
    Next
    INDEX
    Explanations

    mentions of deceased individuals and their surviving relatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }{*}{
    -0.52
    $-$
    -0.49
     lenker
    -0.47
    kannya
    -0.47
    gai
    -0.46
    USING
    -0.46
    hafter
    -0.46
     lå
    -0.45
    oga
    -0.45
    $-
    -0.45
    POSITIVE LOGITS
     predeceased
    0.95
     survivors
    0.90
     survived
    0.90
    survi
    0.89
     Survi
    0.86
     mourned
    0.81
    Survivors
    0.79
     Survivors
    0.77
     survivor
    0.74
     surviving
    0.74
    Activations Density 0.019%

    No Known Activations