© 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. 5358
    Prev
    Next
    INDEX
    Explanations

    elements of storytelling that blur genre boundaries

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

    Describing stories, photographs, or albums

    np_acts-logits-general · gemini-2.0-flash

    stories, tales, pictures, photographs describing something

    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
    •Literature
    elements of storytelling that blur genre boundaries

    No Comments

    Negative Logits
    ValueStyle
    -0.71
     étoit
    -0.63
     recevrez
    -0.63
    Personensuche
    -0.61
    存于互联网档案馆
    -0.61
    __*/
    -0.61
    日閲覧
    -0.59
    :✨
    -0.56
    losse
    -0.56
    archiviato
    -0.56
    POSITIVE LOGITS
    reflect
    0.90
     reflect
    0.87
     embodies
    0.82
     taps
    0.82
     reflects
    0.80
     captures
    0.77
     epitom
    0.76
     embody
    0.75
     tapping
    0.74
     encaps
    0.74
    Activations Density 0.569%

    No Known Activations