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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 1906
    Prev
    Next
    INDEX
    Explanations

    elements related to sleep disorders and their associated symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    objPHPExcel
    -0.45
    bmw
    -0.39
    揄
    -0.39
    trail
    -0.37
    borderFill
    -0.37
    canner
    -0.37
     Leal
    -0.36
     CURIAM
    -0.36
    ::~
    -0.36
    рующие
    -0.36
    POSITIVE LOGITS
     sleep
    0.93
    Sleep
    0.77
     SLEEP
    0.76
     Sleep
    0.75
     sleeping
    0.74
     sommeil
    0.71
     sleeps
    0.71
    sleep
    0.71
    SLEEP
    0.71
    睡眠
    0.68
    Activations Density 0.360%

    No Known Activations