© 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. 3968
    Prev
    Next
    INDEX
    Explanations

    proper nouns in the context of pharmaceutical or medical research

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

    Swiss locations or entities

    np_acts-logits-general · gemini-2.0-flash

    Swiss locations and companies

    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
     Williamsburg
    -0.63
    akteur
    -0.63
    XMLSchema
    -0.60
    unnitel
    -0.59
     Parigi
    -0.57
     Haarlem
    -0.54
     Lithuan
    -0.53
     Guadeloupe
    -0.53
     Lecce
    -0.51
     Myrtle
    -0.51
    POSITIVE LOGITS
     Swiss
    1.57
     Switzerland
    1.41
    Swiss
    1.36
     swiss
    1.32
    Switzerland
    1.29
    swiss
    1.15
     Zurich
    1.08
    瑞士
    1.04
     suisse
    1.01
     Schweiz
    0.99
    Activations Density 0.098%

    No Known Activations