© 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. 15-GEMMASCOPE-RES-16K
    11. 4879
    Prev
    Next
    INDEX
    Explanations

    memory allocation and deallocation operations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     automatiques
    -0.55
     onOptions
    -0.54
     cuivre
    -0.52
    PathVariable
    -0.50
     rangs
    -0.49
    ParallelGroup
    -0.48
     tradizione
    -0.48
     oeufs
    -0.47
     Adventist
    -0.47
     Assyrian
    -0.47
    POSITIVE LOGITS
    malloc
    0.81
     malloc
    0.80
    stdlib
    0.77
     allocator
    0.76
     שוליים
    0.73
    ALLOC
    0.72
     allocate
    0.72
     memory
    0.71
     Alloc
    0.70
    Malloc
    0.69
    Activations Density 0.125%

    No Known Activations