© 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. 20-GEMMASCOPE-RES-16K
    11. 11919
    Prev
    Next
    INDEX
    Explanations

    elements related to programming or coding structures

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

    Code snippets/SQL queries

    np_acts-logits-general · gemini-2.0-flash

    configuration/date/settlement words

    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
    IntoConstraints
    -0.43
    findpost
    -0.35
    ViewImports
    -0.33
     convencional
    -0.32
    PyExc
    -0.32
    AutoField
    -0.31
     clásico
    -0.31
    featureID
    -0.30
    Javadoc
    -0.29
    tonsoft
    -0.29
    POSITIVE LOGITS
    verwijspagina
    0.56
    consistency
    0.52
     strto
    0.50
     Consistency
    0.50
     Nora
    0.49
    Symmetry
    0.49
    ultura
    0.48
     Symmetry
    0.47
    Consistency
    0.47
     Settlement
    0.47
    Activations Density 3.519%

    No Known Activations