© 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 EvalsExportsinterp-engineNEWAPI 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. 11743
    Prev
    Next
    INDEX
    Explanations

    the word "of" and its repeated instances in various contexts

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

    "of the"

    np_acts-logits-general · gemini-2.0-flash

    all of the

    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
     مرئيه
    -0.54
    Portale
    -0.52
     propOrder
    -0.49
    modelBuilder
    -0.47
    Rptr
    -0.47
    ?><
    -0.47
    ///</
    -0.45
    BrowserRouter
    -0.45
    migrationBuilder
    -0.44
    createStatement
    -0.43
    POSITIVE LOGITS
     suivants
    0.45
     MAJOR
    0.45
     burbuja
    0.45
     hır
    0.43
    major
    0.42
     חלק
    0.42
     boletín
    0.41
     totalité
    0.40
     redacción
    0.40
    MAJOR
    0.40
    Activations Density 0.155%

    No Known Activations