© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 35723
    Prev
    Next
    INDEX
    Explanations

    instances of the word "displayed" related to data representation or visualization

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

    information displayed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.79
    تقاوى
    -0.75
     Мексичка
    -0.73
    Personendaten
    -0.68
    المناصب
    -0.67
    TagMode
    -0.66
     المعيارى
    -0.66
     Савезне
    -0.65
    DECREF
    -0.64
    хьтан
    -0.62
    POSITIVE LOGITS
     displayed
    1.64
    displayed
    1.41
     displaying
    1.32
    Displayed
    1.29
     displays
    1.09
     exhibited
    1.09
     Display
    0.96
     display
    0.96
    displays
    0.92
     Displays
    0.91
    Activations Density 0.018%

    No Known Activations