© 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. 38-GEMMASCOPE-RES-16K
    11. 10994
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and imports from code snippets

    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
     FAT
    -0.40
    мян
    -0.40
    مصادر
    -0.38
    buds
    -0.38
     Lucio
    -0.38
     ASR
    -0.38
     "+
    -0.37
    انتهای
    -0.37
     mailing
    -0.36
    ouds
    -0.36
    POSITIVE LOGITS
    SharedDtor
    0.65
     سكانية
    0.56
     للاسماء
    0.55
     dAtA
    0.49
     refleja
    0.48
     оригіналу
    0.47
    complexContent
    0.47
     küpe
    0.46
     kotlinx
    0.46
    RTGC
    0.45
    Activations Density 0.227%

    No Known Activations