© 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. 33-GEMMASCOPE-RES-16K
    11. 1120
    Prev
    Next
    INDEX
    Explanations

    references to specific numeric identifiers or values often used in academic citations or documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.66
    TemporalType
    -0.62
    sizeCache
    -0.61
     protoimpl
    -0.61
    談社
    -0.61
    msgTypes
    -0.60
    GEBURTSDATUM
    -0.59
    */].
    -0.58
    MigrationBuilder
    -0.57
     lenker
    -0.56
    POSITIVE LOGITS
    7
    0.83
     sieben
    0.42
     siete
    0.41
    Observaciones
    0.40
    appcompat
    0.39
    ۷
    0.38
     artificiales
    0.37
     ensayos
    0.37
    Ventajas
    0.36
     lumineux
    0.36
    Activations Density 0.824%

    No Known Activations