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. 25-GEMMASCOPE-RES-16K
    6. 8528
    Prev
    Next
    INDEX
    Explanations

    terms and actions related to browser window management and pop-up behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.70
     betweenstory
    -0.66
    новниш
    -0.61
     Italijanski
    -0.58
    SerializedName
    -0.57
     resourceCulture
    -0.56
    Autoritní
    -0.55
    ItemBackground
    -0.54
    ValueGeneration
    -0.54
     '\\;'
    -0.53
    POSITIVE LOGITS
     window
    1.45
     Window
    1.25
    window
    1.24
    Window
    1.20
     windows
    1.14
     WINDOW
    1.07
    窗口
    1.01
     maximized
    0.98
     ventana
    0.97
     janela
    0.91
    Activations Density 0.368%

    No Known Activations