Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13056
    Prev
    Next
    INDEX
    Explanations

    references to Angular components and error indications related to "not found."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     omit
    -0.45
    合
    -0.41
    wapV
    -0.40
     Uncertain
    -0.40
    obo
    -0.39
     OMITTED
    -0.39
     punctuation
    -0.39
     soften
    -0.38
    obec
    -0.38
    LayoutPanel
    -0.38
    POSITIVE LOGITS
     Product
    0.84
    Product
    0.77
    的产品
    0.63
     productId
    0.62
     Products
    0.61
    ProductType
    0.61
     Producto
    0.60
     getProduct
    0.59
    ProductID
    0.58
    ProductId
    0.57
    Activations Density 0.121%

    No Known Activations