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-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 852
    Prev
    Next
    INDEX
    Explanations

    references to Java Swing GUI components and their associated events

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

    "swing" or "event" related to Java

    np_acts-logits-general · gemini-2.0-flash

    javax.swing events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    DockStyle
    -0.70
    posedge
    -0.63
    webElementXpaths
    -0.62
     disambiguazione
    -0.58
    󠁣
    -0.54
    ỏa
    -0.54
    gameserver
    -0.53
     nakalista
    -0.53
    tonode
    -0.52
    routeProvider
    -0.52
    POSITIVE LOGITS
     initComponents
    0.76
     Swing
    0.56
    FormTagHelper
    0.52
    Swing
    0.50
    swing
    0.48
    WithIOException
    0.47
     swing
    0.45
    Household
    0.43
    amssymb
    0.43
     improvised
    0.42
    Activations Density 0.028%

    No Known Activations