© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 115326
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "number" in various contexts

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

    a number of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forêts
    -0.46
     fronteras
    -0.46
     Gdy
    -0.42
     Belajar
    -0.42
    Vezi
    -0.42
     Anmeldung
    -0.41
     épaules
    -0.41
     Rojas
    -0.41
     Tecnología
    -0.41
     Educação
    -0.40
    POSITIVE LOGITS
     number
    0.87
     many
    0.83
     ſeveral
    0.82
     numerous
    0.79
     several
    0.76
     numbers
    0.72
     ряд
    0.71
     dozens
    0.69
     feveral
    0.67
     ряда
    0.67
    Activations Density 0.008%

    No Known Activations