© 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. 7785
    Prev
    Next
    INDEX
    Explanations

    characters and their relationships in narratives

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

    Character descriptions and portrayals

    np_acts-logits-general · gemini-2.0-flash

    character descriptions and portrayals

    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
    createCanvas
    -0.76
    出版年
    -0.67
    verages
    -0.66
     setuptools
    -0.61
    andaag
    -0.59
    WaitGroup
    -0.58
     autorytatywna
    -0.57
    ientôt
    -0.55
     abstrait
    -0.54
     geométrico
    -0.53
    POSITIVE LOGITS
     character
    0.99
     subplot
    0.95
     characters
    0.86
     personaggio
    0.85
     onscreen
    0.84
     personaje
    0.84
     backstory
    0.83
     foreshadow
    0.83
    character
    0.79
    Character
    0.78
    Activations Density 0.511%

    No Known Activations