© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 52275
    Prev
    Next
    INDEX
    Explanations

    programming commands or keywords related to code structure and functionality

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

    switch statement cases

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    +#+#
    -0.62
    transQ
    -0.54
    pexpr
    -0.54
     CallOverrides
    -0.54
     שוליים
    -0.53
     initComponents
    -0.53
     JpaRepository
    -0.52
     disambiguazione
    -0.49
     CreateTagHelper
    -0.49
    migrationBuilder
    -0.48
    POSITIVE LOGITS
    BufferException
    0.50
    msgTypes
    0.49
    éez
    0.38
    fillType
    0.38
     EClass
    0.37
    WaitGroup
    0.36
    case
    0.35
    misión
    0.34
    CASE
    0.34
     vực
    0.32
    Activations Density 0.001%

    No Known Activations