© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 10808
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to device drivers and hardware 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
     invokingState
    -0.42
     بيها
    -0.41
    pushFollow
    -0.39
    SequentialGroup
    -0.39
    曖昧さ回避
    -0.38
    crollView
    -0.37
    Titus
    -0.37
     Mahal
    -0.37
     referrerpolicy
    -0.36
     Kuru
    -0.36
    POSITIVE LOGITS
     driver
    1.02
     drivers
    0.96
     Driver
    0.84
     Drivers
    0.82
     Treiber
    0.81
    driver
    0.80
    Driver
    0.76
    drivers
    0.75
    Drivers
    0.72
     device
    0.67
    Activations Density 0.944%

    No Known Activations