© 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. 16-GEMMASCOPE-RES-16K
    11. 8341
    Prev
    Next
    INDEX
    Explanations

    proper nouns, particularly related to locations and legal references

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

    Colorado or Kansas legal context

    np_acts-logits-general · gemini-2.0-flash

    US states and European cities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     I
    -0.54
     im
    -0.50
     Nico
    -0.47
     San
    -0.46
     Andre
    -0.46
    Meredith
    -0.45
     Gauthier
    -0.45
    BUTTON
    -0.45
     (
    -0.45
    Chir
    -0.44
    POSITIVE LOGITS
    parsedMessage
    1.26
     Rajasthan
    1.15
     ſche
    1.05
     Bronco
    1.03
     pleaſure
    1.03
    Tembelea
    1.01
     Broncos
    1.01
     nakalista
    1.00
     ſeveral
    0.99
     itſelf
    0.99
    Activations Density 0.544%

    No Known Activations