© 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. 6090
    Prev
    Next
    INDEX
    Explanations

    technical terms related to automotive components and their functionality

    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
    transQ
    -0.49
    setVerticalGroup
    -0.49
    tvguidetime
    -0.48
    ftagPool
    -0.46
    ContentAsync
    -0.43
     consultato
    -0.39
    llung
    -0.37
    istoitu
    -0.36
    msgTypes
    -0.36
    plotlib
    -0.35
    POSITIVE LOGITS
     drive
    3.39
     driving
    3.23
     driver
    3.22
     drives
    3.13
     Drive
    3.00
     drivers
    2.98
    drive
    2.95
     Driving
    2.86
    Drive
    2.86
     Driver
    2.84
    Activations Density 0.944%

    No Known Activations