© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 2673
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to Android UI layouts and resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iprot
    -0.54
    p
    -0.45
    SequentialGroup
    -0.44
     
    -0.44
      
    -0.40
     …
    -0.39
     in
    -0.39
    (
    -0.39
    AlterField
    -0.39
    Â
    -0.38
    POSITIVE LOGITS
    脚注の使い方
    1.08
     بيها
    1.05
    出版年
    0.99
    abestanden
    0.92
    ValueStyle
    0.89
    новниш
    0.88
    Демографія
    0.85
     tartalomajánló
    0.82
    ItemBackground
    0.81
     linkovi
    0.79
    Activations Density 0.274%

    No Known Activations