© 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. 5830
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords, specifically syntax elements and variable declarations

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

    Programming language constants

    np_acts-logits-general · gemini-2.0-flash

    repeated variable declarations

    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
     määrä
    -0.51
    eeded
    -0.50
    ؤلاء
    -0.49
    bní
    -0.48
     tarko
    -0.47
     idéia
    -0.46
     svého
    -0.46
     chiam
    -0.45
     doInBackground
    -0.44
     aastal
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.80
     مرئيه
    0.76
     المعيارى
    0.72
    GEBURTSDATUM
    0.72
     autorytatywna
    0.71
    java
    0.69
    Autoritní
    0.69
     pinulongan
    0.67
    UnusedPrivate
    0.67
     الحره
    0.67
    Activations Density 0.077%

    No Known Activations