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

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 4179
    Prev
    Next
    INDEX
    Explanations

    specific references to the noun "the" in various contexts related to environmental issues and inventions

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

    "The" followed by technical words

    np_acts-logits-general · gemini-2.0-flash

    definite article precedes common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     split
    -0.39
     Linder
    -0.34
     satunya
    -0.33
    impôt
    -0.33
     güven
    -0.32
     divided
    -0.31
     ویکی‌پدی
    -0.30
     타
    -0.30
     attaques
    -0.29
     volante
    -0.29
    POSITIVE LOGITS
    aarrggbb
    0.73
     Wiktionnaire
    0.59
    Хьажоргаш
    0.55
     ujednoznacz
    0.54
    tvguidetime
    0.50
     extremities
    0.50
     onOptions
    0.49
    OGND
    0.49
    cripts
    0.49
    numerusform
    0.49
    Activations Density 1.155%

    No Known Activations