© 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. 9829
    Prev
    Next
    INDEX
    Explanations

    mathematical and statistical terms or symbols associated with equations and functions

    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
     يتيمه
    -0.63
    ViewImports
    -0.63
    الحياه
    -0.59
     المعيارى
    -0.58
    Glej
    -0.57
    /**
    -0.57
    KommentareTeilen
    -0.56
    ValueStyle
    -0.53
     चीज़ों
    -0.53
    /*
    -0.52
    POSITIVE LOGITS
     ,
    0.52
    =:
    0.46
     implies
    0.39
    .
    0.38
    ,
    0.36
     ，
    0.35
     holds
    0.35
    leads
    0.35
         
    0.35
    Tent
    0.35
    Activations Density 2.768%

    No Known Activations