© 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. 1028
    Prev
    Next
    INDEX
    Explanations

    terms related to trade negotiations and governmental decisions

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

    Follows certain nouns (officials, cost, land)

    np_acts-logits-general · gemini-2.0-flash

    German words

    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
     impactful
    -1.23
    . 
    -1.21
     incentiv
    -1.18
     COVID
    -1.16
     onboarding
    -1.12
     
    -1.10
    COVID
    -1.10
    nullptr
    -1.05
     https
    -1.02
    https
    -1.01
    POSITIVE LOGITS
     idéia
    1.52
     muß
    1.14
     daß
    1.11
     läßt
    1.09
     Daß
    1.05
    faßt
    1.01
     Moslem
    1.01
     mußte
    0.95
     mußten
    0.88
     Miß
    0.86
    Activations Density 1.625%

    No Known Activations