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

    Neuronpedia

    Jacobian LensNEW
    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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 4040
    Prev
    Next
    INDEX
    Explanations

    references to academic studies or citations

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

    publications with et al. and year

    np_acts-logits-general · gemini-2.0-flash

    citations and years

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.75
    rungsseite
    -0.68
     CanadaChoose
    -0.57
     initComponents
    -0.51
     SafeMath
    -0.47
     चीज़ों
    -0.47
    ]<<
    -0.47
    ждународ
    -0.45
    invokeLater
    -0.45
     wiſſen
    -0.45
    POSITIVE LOGITS
    ViewImports
    0.48
     للاسماء
    0.41
    MathML
    0.38
     foal
    0.32
    AccessorTable
    0.31
    šinou
    0.31
    ună
    0.31
    oiseau
    0.31
     leyendas
    0.30
     conversely
    0.30
    Activations Density 0.727%

    No Known Activations