Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11410
    Prev
    Next
    INDEX
    Explanations

    technical specifications related to graphics processing units (GPUs)

    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
    transQ
    -0.54
     ModelExpression
    -0.53
    IntoConstraints
    -0.47
    はじめに
    -0.45
     Photocase
    -0.44
    ########.
    -0.43
    Risultati
    -0.42
    Autoritní
    -0.41
    RFC
    -0.39
     RFC
    -0.39
    POSITIVE LOGITS
     graphics
    1.19
     GPU
    1.03
     Graphics
    1.02
     graphic
    0.96
     GPUs
    0.96
    Graphics
    0.91
    graphics
    0.91
     Nvidia
    0.91
     Grafik
    0.89
     grafik
    0.88
    Activations Density 0.222%

    No Known Activations