© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7908
    Prev
    Next
    INDEX
    Explanations

    function calls and their relationships to data structures in programming contexts

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

    Code, software, and programming terms

    np_acts-logits-general · gemini-2.0-flash

    technical code and data terms

    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
     Wiktionnaire
    -0.70
    ()?;
    -0.69
    ("*");
    -0.68
     oprot
    -0.67
     tartalomajánló
    -0.67
     ''),
    -0.66
    ">',
    -0.66
    ('');
    -0.65
    ::*;
    -0.63
    +='
    -0.63
    POSITIVE LOGITS
     pinulongan
    0.74
    (
    0.73
     (
    0.72
    （
    0.63
    MLLoader
    0.62
    ANTLR
    0.58
     onCancelled
    0.58
     InputDecoration
    0.56
    AlterField
    0.56
    Hozzáférés
    0.52
    Activations Density 0.133%

    No Known Activations