© 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. 15259
    Prev
    Next
    INDEX
    Explanations

    references to code or documentation annotations

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

    Tokens followed by "link"

    np_acts-logits-general · gemini-2.0-flash

    assisted CVD

    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
    EndProject
    -0.75
    iausi
    -0.67
     cherchés
    -0.66
    ArgumentParser
    -0.66
     ContentValues
    -0.62
     acaso
    -0.62
    Rohy
    -0.61
    getMenuInflater
    -0.60
    BoxShadow
    -0.57
     ligiloj
    -0.56
    POSITIVE LOGITS
     {@
    1.00
    {@
    0.81
    link
    0.81
     Link
    0.71
     link
    0.70
     cref
    0.70
    >{@
    0.67
    bkz
    0.67
     LINK
    0.64
     للاسماء
    0.62
    Activations Density 0.372%

    No Known Activations