© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8333
    Prev
    Next
    INDEX
    Explanations

    import statements and component definitions in React code

    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
    transQ
    -0.69
     дописавши
    -0.65
     للمعارف
    -0.61
     AssemblyCompany
    -0.57
    writeFieldEnd
    -0.57
    __":
    
    -0.56
    AndEndTag
    -0.55
    GTCX
    -0.55
    AnchorTagHelper
    -0.54
     HttpNotFound
    -0.54
    POSITIVE LOGITS
    react
    0.73
     react
    0.46
    UnityEngine
    0.45
    karet
    0.39
     UnityEngine
    0.39
    https
    0.36
    swiper
    0.35
    React
    0.35
     henvisninger
    0.35
     React
    0.35
    Activations Density 0.188%

    No Known Activations