© 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. 20-GEMMASCOPE-RES-16K
    11. 1115
    Prev
    Next
    INDEX
    Explanations

    instances of the article "a" and variations like "an."

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

    articles ("a" with high activation values across various contexts).

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     honneur
    -0.61
     intenção
    -0.49
     inscripción
    -0.49
     pretože
    -0.47
    queles
    -0.47
     tarko
    -0.46
     princí
    -0.46
     vôtre
    -0.45
     intención
    -0.43
     obligación
    -0.43
    POSITIVE LOGITS
     a
    1.43
     an
    1.03
    niſſe
    0.90
     একটি
    0.88
    ſſung
    0.84
    einen
    0.83
     queſto
    0.83
     ஒரு
    0.82
    <unused3>
    0.82
    [@BOS@]
    0.82
    Activations Density 1.295%

    No Known Activations