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. 12-GEMMASCOPE-RES-16K
    6. 7384
    Prev
    Next
    INDEX
    Explanations

    references to Windows Forms and related Swing classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.98
    FunctionFlags
    -0.78
    енча
    -0.77
    transQ
    -0.73
     kasarigan
    -0.71
    millimeters
    -0.70
    TagMode
    -0.70
    aarrggbb
    -0.68
    ()));
    
    -0.67
    ())));
    -0.67
    POSITIVE LOGITS
    Forms
    1.46
    WebControls
    0.99
     MessageBoxIcon
    0.91
     EventArgs
    0.77
     Forms
    0.75
    forms
    0.67
    FORMS
    0.66
     forms
    0.65
     FORMS
    0.63
    JFrame
    0.60
    Activations Density 0.005%

    No Known Activations