© 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. 9587
    Prev
    Next
    INDEX
    Explanations

    statistical performance metrics in sports contexts

    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
     betweenstory
    -0.86
     NSCoder
    -0.68
    SharedCtor
    -0.66
    InjectAttribute
    -0.63
     CreateTagHelper
    -0.63
     propOrder
    -0.59
     invokingState
    -0.58
     informée
    -0.57
    Erreferentziak
    -0.56
    MemoryWarning
    -0.55
    POSITIVE LOGITS
     compared
    0.51
     overall
    0.50
     against
    0.49
     while
    0.48
     spread
    0.46
     including
    0.45
     despite
    0.45
     Including
    0.39
     total
    0.38
     heading
    0.37
    Activations Density 0.186%

    No Known Activations