© 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. 2138
    Prev
    Next
    INDEX
    Explanations

    words related to data extraction processes

    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
    fontaine
    -0.84
    modelBuilder
    -0.84
    wpdb
    -0.79
    مصادر
    -0.78
    SceneManagement
    -0.76
     onOptions
    -0.76
    antMatchers
    -0.75
    WithMany
    -0.71
    ьаж
    -0.70
    ControllerAdvice
    -0.70
    POSITIVE LOGITS
     extracts
    1.75
     extract
    1.71
     Extract
    1.69
    Extract
    1.67
     extracted
    1.63
     EXTRACT
    1.63
     Extracts
    1.62
     extraction
    1.61
     Extraction
    1.57
    extract
    1.52
    Activations Density 0.200%

    No Known Activations