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. 24-GEMMASCOPE-RES-16K
    6. 14189
    Prev
    Next
    INDEX
    Explanations

    Java utility classes and their usage in programming

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

    periods before Java collection types

    np_acts-logits-general · gemini-2.0-flash

    java programming constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.78
    parsedMessage
    -0.77
    WriteLiteral
    -0.73
    Personensuche
    -0.66
    AsUp
    -0.65
     onCancelled
    -0.61
     AssemblyProduct
    -0.61
    WebMethod
    -0.60
    webElementXpaths
    -0.59
    ForValue
    -0.59
    POSITIVE LOGITS
    logging
    0.80
    Arrays
    0.78
    regex
    0.75
    ArrayList
    0.75
    concurrent
    0.71
    Iterator
    0.70
    stream
    0.69
    List
    0.69
    HashMap
    0.69
    zip
    0.67
    Activations Density 0.042%

    No Known Activations