© 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. 14426
    Prev
    Next
    INDEX
    Explanations

    occurrences of articles in various forms

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

    French, Spanish, or Portuguese articles (la, le, o)

    np_acts-logits-general · gemini-2.0-flash

    articles or words starting with 'l'

    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
     Cæsar
    -0.96
     Shakspeare
    -0.92
     Monfieur
    -0.91
     houſe
    -0.90
     Mahomet
    -0.89
     Huguen
    -0.89
     itſelf
    -0.89
     Esau
    -0.88
    seamnă
    -0.88
     ་་
    -0.87
    POSITIVE LOGITS
     most
    1.08
     same
    0.99
     last
    0.98
     latter
    0.90
     entire
    0.90
     la
    0.88
     whole
    0.87
     final
    0.86
     rest
    0.85
     p
    0.82
    Activations Density 0.019%

    No Known Activations