© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 10476
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to scientific processes and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tudo
    -0.65
    everything
    -0.63
     sesuatu
    -0.61
    anything
    -0.61
     lainnya
    -0.61
    something
    -0.60
     всичко
    -0.59
    Everything
    -0.59
    Others
    -0.59
     semuanya
    -0.57
    POSITIVE LOGITS
     commercially
    0.79
     experimentally
    0.71
     randomly
    0.71
     clinically
    0.68
     spontaneously
    0.66
     moderately
    0.66
     vertically
    0.65
     longitudinally
    0.65
     highly
    0.65
     privately
    0.65
    Activations Density 4.606%

    No Known Activations