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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 14-GEMMASCOPE-RES-16K
    6. 3288
    Prev
    Next
    INDEX
    Explanations

    elements related to memory allocation and potential buffer overflow vulnerabilities in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.65
    jooq
    -0.60
    WireFormatLite
    -0.60
     onOptions
    -0.59
    Спасылкі
    -0.57
     jSON
    -0.56
    trk
    -0.55
     defStyle
    -0.55
     FILED
    -0.55
    Facades
    -0.55
    POSITIVE LOGITS
    stdlib
    0.81
     malloc
    0.79
     Alloc
    0.79
    malloc
    0.78
     memory
    0.77
     allocate
    0.76
     allocation
    0.75
     alloc
    0.74
     allocations
    0.73
     allocator
    0.72
    Activations Density 0.174%

    No Known Activations