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. 4-GEMMASCOPE-RES-16K
    6. 16006
    Prev
    Next
    INDEX
    Explanations

    terms related to user interface components and graphical elements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.78
     متعلقه
    -0.78
     AssemblyCulture
    -0.73
    :✨
    -0.70
     ContentValues
    -0.69
    帖最后由
    -0.67
    WarningLevel
    -0.67
     <=",
    -0.66
    исленность
    -0.66
     &___
    -0.66
    POSITIVE LOGITS
    fxml
    0.87
    WebControls
    0.82
     window
    0.76
    JFrame
    0.71
     screen
    0.71
     screens
    0.70
    GUI
    0.68
    Window
    0.67
    window
    0.63
     JFrame
    0.63
    Activations Density 0.638%

    No Known Activations