© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 29847
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to data structures and functions in programming, particularly those involving queues and scheduling operations

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

    queue operations and 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 @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GenerationType
    -0.44
     ویکی‌پدیا
    -0.41
    ItemLayout
    -0.38
    Mike
    -0.38
    OrBuilder
    -0.36
    tableFuture
    -0.35
     Verhält
    -0.35
    t
    -0.35
    modelBuilder
    -0.34
    ciclop
    -0.33
    POSITIVE LOGITS
    enqueue
    3.25
     enqueue
    2.48
    Enqueue
    2.30
     dequeue
    1.42
    dequeue
    1.25
    Dequeue
    1.16
    queued
    0.92
    QUEUE
    0.77
     queuing
    0.75
     Enrollment
    0.73
    Activations Density 0.001%

    No Known Activations