© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105949
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming expressions, variables, and operations related to test cases and requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.68
     considérons
    -0.54
    RefNanny
    -0.54
     ModelExpression
    -0.48
    keyColumn
    -0.46
     ویکی‌پدیا
    -0.42
     OFDb
    -0.42
    
    -0.42
    rungsseite
    -0.42
    mybatisplus
    -0.42
    POSITIVE LOGITS
     Monfieur
    0.42
     Infór
    0.41
     tajam
    0.41
    IBarButtonItem
    0.40
     Ausbau
    0.40
     jäsen
    0.40
     Italij
    0.40
     yến
    0.39
     poffe
    0.39
     necessariamente
    0.39
    Activations Density 0.223%

    No Known Activations