© 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. 34-GEMMASCOPE-RES-16K
    11. 10002
    Prev
    Next
    INDEX
    Explanations

    connections and references to scholarly essays and intellectual discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.48
    queryInterface
    -0.35
    TagMode
    -0.34
    orphism
    -0.34
    msgTypes
    -0.32
    PreferredItem
    -0.31
     Verhält
    -0.30
    colhead
    -0.30
    дравству
    -0.30
     déliv
    -0.30
    POSITIVE LOGITS
     gathered
    2.20
     gather
    2.03
     gathering
    1.99
     gathers
    1.98
     rassemb
    1.93
     assembled
    1.87
     aggregation
    1.87
     assembling
    1.80
     assemble
    1.78
     aggregated
    1.78
    Activations Density 1.180%

    No Known Activations