© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7853
    Prev
    Next
    INDEX
    Explanations

    references to life, death, resurrection, and the relationship between the living and the dead

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

    death and resurrection

    np_acts-logits-general · gemini-2.0-flash

    dead, death, and resurrection

    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
     galaxia
    -0.45
     davon
    -0.45
    misu
    -0.44
     Cabot
    -0.43
     buckwheat
    -0.43
    FetchType
    -0.43
    Galaxy
    -0.41
    insatz
    -0.40
    πι
    -0.40
    veis
    -0.39
    POSITIVE LOGITS
     dead
    1.98
    dead
    1.70
     Dead
    1.60
    Dead
    1.55
     DEAD
    1.53
    DEAD
    1.33
     мерт
    1.33
     death
    1.31
     muertos
    1.28
     morts
    1.27
    Activations Density 0.153%

    No Known Activations