© 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
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8981
    Prev
    Next
    INDEX
    Explanations

    data types and memory allocation keywords in programming code

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

    code tokens for primitive numeric types and explicit casts, especially around floating-point literals and type conversions in C/Java-like code.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    type casting operations in programming code, particularly casts to numeric types like `float`, `double`, `int`, `long`, and `char`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    richTextPanel
    -0.60
     TestBed
    -0.58
     >=",
    -0.48
     ferons
    -0.47
    StructEnd
    -0.46
     trekken
    -0.46
    $_['
    -0.45
     الوطنيه
    -0.45
    ulmuş
    -0.44
     musuh
    -0.44
    POSITIVE LOGITS
    醐
    0.49
    GEBURTSDATUM
    0.49
     ​
    0.40
    MigrationBuilder
    0.39
    /"+
    0.39
     int
    0.39
    
    0.38
     dem
    0.36
    DetailActivity
    0.36
    ِل
    0.36
    Activations Density 0.089%

    No Known Activations