© 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. 24-GEMMASCOPE-RES-16K
    11. 5020
    Prev
    Next
    INDEX
    Explanations

    references to deaths and significant life events

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

    Followed by "death"

    np_acts-logits-general · gemini-2.0-flash

    's death or retirement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.61
    PLIED
    -0.58
     continúas
    -0.57
     متحده
    -0.56
    nitten
    -0.56
     afectada
    -0.54
     mariée
    -0.52
    lahraga
    -0.52
    WriteBarrier
    -0.51
     restantes
    -0.50
    POSITIVE LOGITS
     departure
    1.17
     arrival
    1.15
     death
    1.11
     demise
    1.02
     disappearance
    1.00
     return
    0.93
     sudden
    0.92
     passing
    0.89
     defeat
    0.88
     capture
    0.82
    Activations Density 0.407%

    No Known Activations