© 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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 17379
    Prev
    Next
    INDEX
    Explanations

    references to NVIDIA and CUDA technology within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    CUDA, Nvidia, AMD, GPUs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.47
    writerow
    -0.45
    interopRequire
    -0.44
    ResponseWriter
    -0.42
    InSection
    -0.42
    tableFuture
    -0.41
    OCCURRED
    -0.41
    ({_
    -0.41
    WithFormat
    -0.40
    verifyException
    -0.40
    POSITIVE LOGITS
     Nvidia
    1.16
     NVIDIA
    1.08
    Nvidia
    1.07
     nvidia
    1.02
    NVIDIA
    0.95
    nvidia
    0.85
     GeForce
    0.73
     geforce
    0.71
     GPUs
    0.66
     GPU
    0.60
    Activations Density 0.012%

    No Known Activations