© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14305
    Prev
    Next
    INDEX
    Explanations

    keywords related to type definitions and namespace usage in programming code

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

    C++ type declarations: "typedef" and "using"

    np_acts-logits-general · gemini-2.0-flash

    C++ type definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
     ſever
    -0.55
    SqlClient
    -0.55
     PIB
    -0.53
     AssemblyProduct
    -0.49
     stmt
    -0.48
     ſche
    -0.46
     patrio
    -0.45
     invokingState
    -0.44
    wantErr
    -0.43
     QLabel
    -0.43
    POSITIVE LOGITS
    typedef
    1.00
     typedef
    0.76
    RectangleBorder
    0.56
     propOrder
    0.54
     beginnetje
    0.52
     ويكيپيديا
    0.51
    Bronnen
    0.48
    using
    0.48
    xmlns
    0.47
     تضيفلها
    0.46
    Activations Density 0.154%

    No Known Activations