© 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. 18-GEMMASCOPE-RES-16K
    11. 3334
    Prev
    Next
    INDEX
    Explanations

    key structural elements and organization in written texts

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

    Beginning of numbered sections or chapters

    np_acts-logits-general · gemini-2.0-flash

    first chapter or section

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opsida
    -0.66
     AssemblyCulture
    -0.64
    RetentionPolicy
    -0.63
     ModelExpression
    -0.62
    Бахар
    -0.62
    HasAnnotation
    -0.60
    出版年
    -0.60
    VIAF
    -0.60
     VIAF
    -0.58
     ComVisible
    -0.57
    POSITIVE LOGITS
     chapter
    1.55
     chapters
    1.48
     Chapter
    1.33
     section
    1.33
    chapter
    1.32
    Chapter
    1.29
     sections
    1.23
     Chapters
    1.19
    Chapters
    1.17
    chapters
    1.12
    Activations Density 0.445%

    No Known Activations