© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11677
    Prev
    Next
    INDEX
    Explanations

    elements related to programming and configuration files

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

    XML or Gradle build configurations

    np_acts-logits-general · gemini-2.0-flash

    project build configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    queryInterface
    -0.56
     breath
    -0.55
    Eloquent
    -0.52
    WritableDatabase
    -0.47
    Operators
    -0.45
     Spre
    -0.45
     điệu
    -0.45
     breat
    -0.44
     Freiw
    -0.43
    ardians
    -0.43
    POSITIVE LOGITS
     Build
    0.86
     build
    0.85
     project
    0.81
    Build
    0.77
    build
    0.76
    project
    0.75
     BUILD
    0.72
     compile
    0.71
     dependency
    0.71
     Project
    0.70
    Activations Density 1.004%

    No Known Activations