© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8688
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific processes or methods

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

    scientific and technical word stems, particularly those related to biochemistry and molecular structures.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    e
    -0.53
    goTo
    -0.53
     Farley
    -0.50
    ,
    -0.49
     Anexo
    -0.48
     Koffer
    -0.47
    getMap
    -0.47
     Cardona
    -0.46
     Sicht
    -0.46
     Ketten
    -0.45
    POSITIVE LOGITS
    ьаж
    0.67
    ibrill
    0.64
     voed
    0.62
    strator
    0.60
    theilen
    0.60
     AssemblyCulture
    0.60
     않
    0.60
     zoude
    0.59
    ſcher
    0.58
    toggler
    0.57
    Activations Density 0.822%

    No Known Activations