© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 103510
    Prev
    Next
    INDEX
    Explanations

    terms related to programming or technical issues, particularly around function definitions and resource management

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

    Punctuation marks and special characters used in various code and text formats, including commas, periods, parentheses, and angle brackets, often occurring at boundaries between different syntactic elements.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     ModelExpression
    -0.45
    ollectionView
    -0.37
    oredCriteria
    -0.37
    quelize
    -0.35
    AttributedString
    -0.35
     CanadaChoose
    -0.32
    kulum
    -0.32
     ContentValues
    -0.32
     Widodo
    -0.32
     foramen
    -0.31
    POSITIVE LOGITS
    rungsseite
    0.61
     exposure
    0.52
     exposures
    0.51
    WriteBarrier
    0.49
    exposure
    0.48
    رشف
    0.48
    Exposure
    0.47
     exposing
    0.47
    ViewFeatures
    0.47
    Rüyada
    0.46
    Activations Density 0.485%

    No Known Activations