© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 10789
    Prev
    Next
    INDEX
    Explanations

    mentions of historical events and their lasting impacts

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

    "today" or current events

    np_acts-logits-general · gemini-2.0-flash

    still today

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.70
     allAfrica
    -0.45
    <![
    -0.44
     Italijanski
    -0.44
     bershka
    -0.44
    marché
    -0.44
     prochains
    -0.43
    alogie
    -0.43
    ixeira
    -0.43
    Normally
    -0.43
    POSITIVE LOGITS
     today
    2.48
     aujourd
    2.06
     heute
    1.99
    today
    1.98
     Today
    1.96
     hoje
    1.94
     oggi
    1.90
    Today
    1.89
     nowadays
    1.86
     heutigen
    1.83
    Activations Density 1.680%

    No Known Activations