© 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. 14-GEMMASCOPE-RES-16K
    11. 7852
    Prev
    Next
    INDEX
    Explanations

    references to various types of pockets and items contained within them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.72
    Erreferentziak
    -0.47
    Географиясе
    -0.45
    modelBuilder
    -0.45
     tehdä
    -0.42
     apellidos
    -0.41
     igång
    -0.41
    Попис
    -0.41
     predicate
    -0.39
     pousser
    -0.38
    POSITIVE LOGITS
     pocket
    1.03
     Pocket
    0.95
    pocket
    0.93
    Pocket
    0.93
     Wallet
    0.80
     wallet
    0.79
     pockets
    0.79
     tasche
    0.79
     Pockets
    0.78
     purse
    0.75
    Activations Density 0.123%

    No Known Activations