© 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. 3-GEMMASCOPE-RES-16K
    11. 5247
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and indications of pauses in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addContainerGap
    -0.43
    Lain
    -0.39
     Daß
    -0.39
    ThroughAttribute
    -0.38
    arXiv
    -0.37
     Lain
    -0.37
    addGap
    -0.36
     distingu
    -0.36
     distinguer
    -0.36
     стар
    -0.35
    POSITIVE LOGITS
     controlled
    0.81
     Controlled
    0.80
    Controlled
    0.75
    controlled
    0.71
     uncontrolled
    0.62
    MigrationBuilder
    0.61
     EconPapers
    0.61
    BagConstraints
    0.61
     controlado
    0.55
     informée
    0.54
    Activations Density 0.230%

    No Known Activations