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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 22-GEMMASCOPE-RES-16K
    6. 11027
    Prev
    Next
    INDEX
    Explanations

    terms related to display technology and specifications

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

    Display technologies, especially LCD and LED

    np_acts-logits-general · gemini-2.0-flash

    display technology

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Longfellow
    -0.57
    styleable
    -0.54
    addContainerGap
    -0.53
    UpInside
    -0.52
    ftagPool
    -0.51
     Helsinki
    -0.51
     Barth
    -0.49
    Autoritní
    -0.48
    bolista
    -0.48
     Rosalie
    -0.48
    POSITIVE LOGITS
     Display
    0.97
     display
    0.97
     LCD
    0.91
    Display
    0.86
     displays
    0.81
    display
    0.81
     Displays
    0.80
     DISPLAY
    0.79
     refresh
    0.78
    Displays
    0.75
    Activations Density 0.407%

    No Known Activations