© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 34-GEMMASCOPE-RES-16K
    6. 10882
    Prev
    Next
    INDEX
    Explanations

    references to geographic features and outdoor recreational activities

    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
    oa̍t
    -0.40
    setCellStyle
    -0.40
    ViewImports
    -0.39
    RectangleBorder
    -0.37
    exels
    -0.35
    */].
    -0.35
     جغرافيا
    -0.34
     mey
    -0.33
     oprot
    -0.32
     iconLine
    -0.32
    POSITIVE LOGITS
     visitor
    1.26
     visitors
    1.21
     Visitor
    1.20
     Visitors
    1.16
     tours
    1.10
     guided
    1.05
     Besucher
    1.05
     pengunjung
    1.05
    Visitors
    1.04
    Visitor
    0.99
    Activations Density 0.186%

    No Known Activations