© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13606
    Prev
    Next
    INDEX
    Explanations

    markers and notation commonly found in scientific documents or court cases

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

    Bulleted list items and numbered list items in documents.

    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
    ρισσότε
    -0.36
     رائ
    -0.36
    겨
    -0.32
    ubro
    -0.32
    XmlAccessType
    -0.32
    INCREF
    -0.31
     decor
    -0.31
    derung
    -0.31
    DIPSETTING
    -0.30
    tagHelper
    -0.30
    POSITIVE LOGITS
    GEBURTSDATUM
    0.76
     виправивши
    0.74
    rungsseite
    0.71
     disambiguazione
    0.67
    NameInMap
    0.66
    intios
    0.61
     שוליים
    0.58
    sizeCache
    0.56
    windowFixed
    0.56
    RegressionTest
    0.56
    Activations Density 0.569%

    No Known Activations