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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15871
    Prev
    Next
    INDEX
    Explanations

    objects and materials associated with writing or crafting

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

    associated with pens and pencils

    np_acts-logits-general · gemini-2.0-flash

    writing and drawing implements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    хьтан
    -0.81
     estekak
    -0.80
    UrlResolution
    -0.75
     Baillargeon
    -0.75
    AnimationsModule
    -0.75
     समीक्षक
    -0.74
     Италијани
    -0.74
     autorytatywna
    -0.73
     متعلقه
    -0.72
     للاسماء
    -0.72
    POSITIVE LOGITS
     pen
    1.74
     pens
    1.58
     Pen
    1.50
     pencil
    1.41
    Pen
    1.36
    pen
    1.34
     Pens
    1.28
     pencils
    1.28
     ink
    1.27
     PEN
    1.25
    Activations Density 0.126%

    No Known Activations