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. 4-GEMMASCOPE-RES-16K
    6. 15825
    Prev
    Next
    INDEX
    Explanations

    references to file operations in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WindowConstants
    -0.69
    bisoft
    -0.67
    AddWithValue
    -0.66
     requestId
    -0.64
    MemoryWarning
    -0.63
    msgSender
    -0.63
     wikipagina
    -0.63
    chtenstein
    -0.62
    Addi
    -0.61
    orsese
    -0.60
    POSITIVE LOGITS
     File
    2.25
    File
    1.99
     file
    1.82
    file
    1.78
     FILE
    1.72
    files
    1.56
    FILE
    1.55
     Files
    1.52
     files
    1.44
    Files
    1.42
    Activations Density 0.060%

    No Known Activations