© 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. 21-GEMMASCOPE-RES-16K
    11. 15358
    Prev
    Next
    INDEX
    Explanations

    elements related to post-apocalyptic themes and characters in narratives

    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
    knex
    -0.50
     flota
    -0.50
     büy
    -0.45
    IGraphics
    -0.44
     mys
    -0.43
     melay
    -0.43
    avigation
    -0.43
    etton
    -0.42
    allergenic
    -0.42
     ilgili
    -0.42
    POSITIVE LOGITS
     zombie
    1.11
     survival
    1.10
     survivors
    1.09
     zombies
    1.05
     Survival
    1.04
     survivor
    1.04
    survival
    1.02
    survi
    0.99
     Survivors
    0.98
    Survivors
    0.96
    Activations Density 0.101%

    No Known Activations