© 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. 38-GEMMASCOPE-RES-16K
    6. 9710
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or structure definitions

    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
     Resources
    -0.81
     Sources
    -0.76
    Resources
    -0.70
     محفوظة
    -0.66
    Sources
    -0.65
     ресурсов
    -0.65
     RESOURCES
    -0.65
     resources
    -0.63
    RESOURCES
    -0.63
     nahilalakip
    -0.63
    POSITIVE LOGITS
    source
    1.05
     source
    0.99
     fuente
    0.54
     sauce
    0.47
    Maurice
    0.46
     sou
    0.44
     cause
    0.44
     Maurice
    0.43
    源
    0.42
    ource
    0.41
    Activations Density 0.181%

    No Known Activations