Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 29742
    Prev
    Next
    INDEX
    Explanations

    terms related to heap memory management in programming

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

    heap, heapq, heap-based

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     propOrder
    -0.69
    StoryboardSegue
    -0.57
    mide
    -0.54
    endcsname
    -0.54
    miller
    -0.52
     Contr
    -0.50
     ν
    -0.50
    OGND
    -0.49
     Ariz
    -0.48
     Walther
    -0.47
    POSITIVE LOGITS
    Heap
    1.13
    heap
    1.12
     heap
    1.10
     Heap
    1.08
     heapq
    1.04
    HEAP
    0.87
     heaps
    0.78
     heaped
    0.73
     desmotivaciones
    0.62
     feroit
    0.61
    Activations Density 0.003%

    No Known Activations