© 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. 13029
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and statistics

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

    pages or minutes

    np_acts-logits-general · gemini-2.0-flash

    pages or chapters

    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
    TagMode
    -0.87
    脚注の使い方
    -0.83
    ContextHolder
    -0.77
    :✨
    -0.76
    tvguidetime
    -0.75
     EconPapers
    -0.75
     незавершена
    -0.75
    TemporalType
    -0.73
     Normdatei
    -0.71
    __*/
    -0.69
    POSITIVE LOGITS
     pages
    0.60
     chapters
    0.52
    pages
    0.49
    p
    0.48
    pp
    0.48
    cxx
    0.48
     pagine
    0.47
     Pages
    0.46
     Chapters
    0.46
     p
    0.45
    Activations Density 0.141%

    No Known Activations