© 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. 293
    Prev
    Next
    INDEX
    Explanations

    code syntax elements and structures in programming

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

    Code, programming, or software development

    np_acts-logits-general · gemini-2.0-flash

    code structures and keywords

    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
    تقاوى
    -0.68
    月号
    -0.61
    AndroidJUnit
    -0.57
     énergé
    -0.57
    adə
    -0.55
    ChildScrollView
    -0.55
     verticales
    -0.55
     réguli
    -0.54
     Spend
    -0.51
    Worth
    -0.51
    POSITIVE LOGITS
    TagMode
    0.61
    typeorm
    0.56
    లాలు
    0.52
    toBeDefined
    0.50
    RegressionTest
    0.49
    MigrationBuilder
    0.47
     LCCN
    0.46
    ۇ
    0.45
    findpost
    0.44
    FieldBuilder
    0.43
    Activations Density 0.015%

    No Known Activations