© 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. 37-GEMMASCOPE-RES-16K
    6. 5974
    Prev
    Next
    INDEX
    Explanations

    attributes related to maintenance and care

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.49
    MessageOf
    -0.49
    roso
    -0.45
     intptr
    -0.45
     GetEnumerator
    -0.44
    Климаты
    -0.43
    nhs
    -0.43
     الرياضيه
    -0.43
    delijk
    -0.42
    Damaged
    -0.42
    POSITIVE LOGITS
     devoid
    0.82
     guilt
    0.74
     odor
    0.69
    ไร
    0.67
     odour
    0.66
     painless
    0.66
     stress
    0.63
    無
    0.63
     completely
    0.62
     fault
    0.62
    Activations Density 0.652%

    No Known Activations