© 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. 4360
    Prev
    Next
    INDEX
    Explanations

    programming language syntax and structure elements

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

    C code accessing struct members, especially pdev

    np_acts-logits-general · gemini-2.0-flash

    code-related programming constructs

    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
    Aholisi
    -0.57
     MainAxisSize
    -0.54
    DebuggerNonUser
    -0.50
     utafitiHapana
    -0.50
    Tembelea
    -0.47
     الحره
    -0.45
    Jeografia
    -0.45
     STREAM
    -0.43
    IntoConstraints
    -0.43
     BoxFit
    -0.42
    POSITIVE LOGITS
    ViewFeatures
    0.47
    styleType
    0.41
     protoimpl
    0.40
     groupBox
    0.38
     ͜ʖ
    0.38
    protoimpl
    0.37
    SharedDtor
    0.36
    menuStrip
    0.36
    InitStructure
    0.36
    rouvez
    0.35
    Activations Density 0.279%

    No Known Activations