© 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. 36-GEMMASCOPE-RES-16K
    6. 15369
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical components and their interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -------------</
    -0.48
    tamine
    -0.42
     snippetHide
    -0.39
     stá
    -0.38
    clable
    -0.38
     quedado
    -0.37
     tarifa
    -0.37
     capucha
    -0.37
     mattress
    -0.36
    ersonic
    -0.36
    POSITIVE LOGITS
     bearings
    1.08
     bearing
    0.96
     gear
    0.93
     Bearings
    0.91
     gears
    0.88
     Bearing
    0.86
     shaft
    0.77
     Gear
    0.77
    Bearing
    0.75
     pulley
    0.75
    Activations Density 0.671%

    No Known Activations