© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13052
    Prev
    Next
    INDEX
    Explanations

    function declarations and definitions in programming code

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

    programming and technical notation, especially code-like syntax tokens, symbols, and all-caps identifiers.

    oai_token-act-pair · gpt-5Triggered 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
     campaigns
    -0.44
     initComponents
    -0.41
    Sempre
    -0.40
    Reporting
    -0.39
    ObjectModel
    -0.38
    rogenic
    -0.38
     franco
    -0.37
     campañas
    -0.37
     firebaseConfig
    -0.37
     succes
    -0.36
    POSITIVE LOGITS
    Hentet
    0.70
    :✨
    0.67
    Personendaten
    0.65
     propOrder
    0.63
     kaarangay
    0.61
    ьаж
    0.60
    NameInMap
    0.60
    Cyfeiriadau
    0.58
    Kjelder
    0.58
     ویکی‌پدی
    0.56
    Activations Density 0.038%

    No Known Activations