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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5516
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific research processes

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

    French locations, people, and events

    np_acts-logits-general · gemini-2.0-flash

    French, Paris, revolution

    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
     ainfi
    -1.13
     nôtre
    -0.99
     auroit
    -0.99
     étoient
    -0.96
     fédé
    -0.95
     auffi
    -0.94
     avoient
    -0.93
     houſe
    -0.91
     plufieurs
    -0.91
     feroit
    -0.90
    POSITIVE LOGITS
     French
    1.09
     France
    1.07
     Paris
    0.96
    France
    0.94
    French
    0.92
     french
    0.92
    PARIS
    0.89
    法国
    0.84
    Paris
    0.83
    FRANCE
    0.80
    Activations Density 0.432%

    No Known Activations