© 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. 30-GEMMASCOPE-RES-16K
    6. 10710
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their gatherings

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

    Country names

    np_acts-logits-general · gemini-2.0-flash

    lists of countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cherchés
    -0.73
    IContainer
    -0.71
    ⟬
    -0.66
    EndGlobalSection
    -0.65
     transférez
    -0.64
    expandindo
    -0.63
    invokeLater
    -0.61
    
    -0.60
     betweenstory
    -0.59
    IUrlHelper
    -0.59
    POSITIVE LOGITS
     China
    0.41
     Chinese
    0.40
     Japan
    0.39
     Australian
    0.38
     Japanese
    0.36
     일본
    0.35
     Austral
    0.33
     South
    0.32
     postIndex
    0.32
     Indian
    0.31
    Activations Density 0.399%

    No Known Activations