© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11314
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific or mathematical notation and formatting

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

    Text after brackets, parentheses, or quotes

    np_acts-logits-general · gemini-2.0-flash

    benzathine coupled with carrier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    gher
    -0.42
    bolo
    -0.41
     collateral
    -0.41
    ategy
    -0.40
    ERVIEW
    -0.40
    ersonal
    -0.40
    quent
    -0.40
    MAT
    -0.40
    quer
    -0.40
     LoggerFactory
    -0.39
    POSITIVE LOGITS
     disambiguazione
    0.53
     enfans
    0.53
     ujednoznacz
    0.49
    WebElementEntity
    0.48
     فريبيس
    0.47
     imprimible
    0.47
    JvmStatic
    0.46
     pareja
    0.44
    Бахар
    0.44
    makeConstraints
    0.43
    Activations Density 1.117%

    No Known Activations