© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 12337
    Prev
    Next
    INDEX
    Explanations

    data structure definitions and manipulations in programming languages

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

    Code, file names, or programming terms

    np_acts-logits-general · gemini-2.0-flash

    first item

    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
    glEnd
    -0.74
    setVerticalGroup
    -0.67
    endregion
    -0.60
     afterwards
    -0.60
     الأخيرة
    -0.58
     terakhir
    -0.55
     последних
    -0.54
     "</
    -0.53
     ostat
    -0.53
     thereafter
    -0.53
    POSITIVE LOGITS
     first
    1.11
    first
    1.04
     pertama
    0.89
    First
    0.88
     erster
    0.88
     primera
    0.87
     eerste
    0.86
    FIRST
    0.85
     first
    0.84
     First
    0.83
    Activations Density 1.179%

    No Known Activations