© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 8619
    Prev
    Next
    INDEX
    Explanations

    terminology and phrases associated with sleep disorders and their effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 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
     fallu
    -0.40
     auroit
    -0.39
    azienda
    -0.38
    hauer
    -0.37
    före
    -0.37
    另
    -0.37
    relsen
    -0.36
     protocol
    -0.36
     Molecules
    -0.36
     Altar
    -0.35
    POSITIVE LOGITS
     sleep
    2.06
     SLEEP
    1.95
     Sleep
    1.92
    Sleep
    1.88
    sleep
    1.81
     sleeping
    1.80
     slept
    1.72
     sleeps
    1.72
    SLEEP
    1.71
     Sleeping
    1.65
    Activations Density 0.160%

    No Known Activations