© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13884
    Prev
    Next
    INDEX
    Explanations

    features and specifications of display technologies

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

    displays, screens, and TFTs

    np_acts-logits-general · gemini-2.0-flash

    display screen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gnore
    -0.39
     Nis
    -0.37
    Migrations
    -0.36
    toolStripButton
    -0.36
    AddTagHelper
    -0.36
    toObject
    -0.35
    Zip
    -0.35
    を紹介
    -0.35
     مخطط
    -0.35
    紹介
    -0.35
    POSITIVE LOGITS
     screen
    0.85
     screens
    0.81
    screen
    0.77
     écran
    0.73
     Screens
    0.69
     màn
    0.67
     Screen
    0.66
     pantalla
    0.66
     touchscreen
    0.66
     écrans
    0.63
    Activations Density 0.209%

    No Known Activations