© 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. 18-GEMMASCOPE-RES-16K
    11. 8415
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to synchronization and locking mechanisms

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

    Code snippets containing "lock" or similar terms

    np_acts-logits-general · gemini-2.0-flash

    command line locks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abestanden
    -0.71
    WebElementEntity
    -0.70
    XMLSchema
    -0.67
    GeneratedMessage
    -0.66
     malah
    -0.65
    __':
    -0.64
    Picked
    -0.64
    $_['
    -0.62
     onItemClick
    -0.62
    migrationBuilder
    -0.62
    POSITIVE LOGITS
    setAccessible
    0.57
     protection
    0.55
    utex
    0.49
     protective
    0.49
    PropertyChanging
    0.48
    lock
    0.48
    BeginContext
    0.47
     protecting
    0.47
     Protection
    0.46
    Locker
    0.45
    Activations Density 0.174%

    No Known Activations