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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7478
    Prev
    Next
    INDEX
    Explanations

    foods that are fried and include various ingredients

    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
     propOrder
    -0.49
    rawDesc
    -0.43
    testng
    -0.39
     Tapas
    -0.39
    ⚐
    -0.39
     quiche
    -0.39
    XmlAccessType
    -0.39
     Signalez
    -0.39
    期刊论文
    -0.38
     nakalista
    -0.38
    POSITIVE LOGITS
     fries
    0.80
    fries
    0.63
     hush
    0.58
     fried
    0.57
     fry
    0.55
     tots
    0.53
     chips
    0.52
     Fry
    0.52
     crispy
    0.52
     wings
    0.51
    Activations Density 0.250%

    No Known Activations