© 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. 10-GEMMASCOPE-RES-16K
    11. 6389
    Prev
    Next
    INDEX
    Explanations

    geographical locations and associated entities, particularly in Connecticut and India

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    таратура
    -0.85
    دانشنامهٔ
    -0.83
     odkazy
    -0.79
     &___
    -0.76
     Grape
    -0.75
    pertino
    -0.73
    BagConstraints
    -0.73
    viewDidLoad
    -0.72
     Racine
    -0.71
     Egli
    -0.71
    POSITIVE LOGITS
     Assam
    0.92
     Iraqi
    0.83
     Iraq
    0.79
    Connecticut
    0.77
     Connecticut
    0.77
    wahati
    0.77
     NSW
    0.77
     العراق
    0.73
    cticut
    0.72
    Iraq
    0.71
    Activations Density 1.102%

    No Known Activations