Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8935
    Prev
    Next
    INDEX
    Explanations

    references to various types of display technologies

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

    technical mentions of display devices and technologies (e.g., "3D display", "touchscreen display", "LCD display")

    oai_token-act-pair · deepseek-r1Triggered by @paul2753

    forms of the word "display" and related terms.

    oai_token-act-pair · deepseek-v3Triggered by @paul2753
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     display
    -2.95
     Display
    -2.73
    display
    -2.73
    Display
    -2.56
     displays
    -2.39
     DISPLAY
    -2.38
     Displays
    -2.14
     displaying
    -2.05
     displayed
    -2.02
    DISPLAY
    -1.94
    POSITIVE LOGITS
    HostException
    0.54
     estimés
    0.54
     ILogger
    0.52
    hagic
    0.50
     IOError
    0.50
    FTFY
    0.49
    Clik
    0.48
     Thessal
    0.47
    ChildScrollView
    0.47
     cherchés
    0.46
    Activations Density 0.125%

    No Known Activations