© 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. 15351
    Prev
    Next
    INDEX
    Explanations

    elements related to apocalyptic themes and zombie narratives

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

    zombies

    np_acts-logits-general · gemini-2.0-flash

    zombie apocalypse

    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
    المشاركات
    -0.51
    IsContent
    -0.51
    IGraphics
    -0.50
     melay
    -0.50
     فريبيس
    -0.49
    rtner
    -0.49
     flota
    -0.48
     puncak
    -0.47
    knex
    -0.47
    etton
    -0.46
    POSITIVE LOGITS
     zombie
    1.08
     zombies
    0.97
     survivors
    0.93
    zombie
    0.90
     Zombie
    0.89
    Zombies
    0.86
     Survivors
    0.86
     survival
    0.85
     survivor
    0.85
    Survivors
    0.84
    Activations Density 0.115%

    No Known Activations