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. 14650
    Prev
    Next
    INDEX
    Explanations

    references to Java's Swing library and its components

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

    Code or math-related tokens

    np_acts-logits-general · gemini-2.0-flash

    swing, Tønder, state penal

    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
     فريبيس
    -0.59
     privées
    -0.56
    
    -0.51
     fiscales
    -0.51
    addCriterion
    -0.50
    forChild
    -0.49
     Pliny
    -0.49
     religieuses
    -0.47
     privadas
    -0.47
    FunctionFlags
    -0.46
    POSITIVE LOGITS
    swing
    1.20
     swing
    1.07
     Swing
    1.06
    Swing
    0.92
     swings
    0.78
     swung
    0.77
     initComponents
    0.77
     swinging
    0.76
     Swin
    0.69
     autorytatywna
    0.67
    Activations Density 0.019%

    No Known Activations