© 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 - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14823
    Prev
    Next
    INDEX
    Explanations

    concepts related to durability and longevity in products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    얻
    -0.37
     embarrassed
    -0.34
    SceneManagement
    -0.33
     diversion
    -0.33
     distracting
    -0.32
     cite
    -0.32
     Friday
    -0.32
     ràng
    -0.32
     embarrassing
    -0.32
    Friday
    -0.32
    POSITIVE LOGITS
     longevity
    0.89
     durability
    0.85
     durable
    0.75
     durabilidad
    0.73
     Durability
    0.71
    durable
    0.68
     lasting
    0.68
     lifetime
    0.68
     Longevity
    0.66
     lifespan
    0.65
    Activations Density 0.327%

    No Known Activations