Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4224
    Prev
    Next
    INDEX
    Explanations

    concepts related to sleep quality and management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Garth
    -0.54
    każ
    -0.43
    seag
    -0.43
    herd
    -0.43
     Rivas
    -0.43
     Tabasco
    -0.43
    icitis
    -0.43
    tikan
    -0.42
     publicKey
    -0.42
     aortic
    -0.42
    POSITIVE LOGITS
     sleep
    2.97
     Sleep
    2.57
     sleeping
    2.54
     SLEEP
    2.45
    sleep
    2.41
     sleeps
    2.39
    Sleep
    2.38
     slept
    2.38
     asleep
    2.24
    sleeping
    2.13
    Activations Density 0.261%

    No Known Activations