© 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 - 65k
    9. 12-GEMMASCOPE-RES-65K
    11. 13703
    Prev
    Next
    INDEX
    Explanations

    descriptors related to the durability and strength of materials or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.60
    WEBPACK
    -0.60
    ADELPHIA
    -0.57
     CreateTagHelper
    -0.56
    jspb
    -0.55
    <bos>
    -0.55
    Diwedd
    -0.52
     GeoNames
    -0.52
    chtigkeit
    -0.52
    出版年
    -0.50
    POSITIVE LOGITS
     durability
    1.02
     indestructible
    0.90
     toughness
    0.85
     sturdy
    0.83
     Durability
    0.82
    tough
    0.79
     robuste
    0.79
     durable
    0.79
     robustness
    0.79
     Tough
    0.76
    Activations Density 0.017%

    No Known Activations