© 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. 5354
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific data and results

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

    Tokens immediately following parentheses

    np_acts-logits-general · gemini-2.0-flash

    organic C and TN

    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
    RenderAtEndOf
    -0.70
     China
    -0.69
    ClientSize
    -0.69
     centimeter
    -0.66
     centi
    -0.65
    Christian
    -0.65
    China
    -0.65
     carbon
    -0.64
     Centers
    -0.64
    Colleen
    -0.64
    POSITIVE LOGITS
    出版年
    0.67
     /\.(
    0.52
     sagesse
    0.51
    ItemLayout
    0.50
    abstractmethod
    0.48
     dignité
    0.47
     soyez
    0.46
    illermo
    0.46
     religieuses
    0.46
     neige
    0.45
    Activations Density 0.664%

    No Known Activations