© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 14484
    Prev
    Next
    INDEX
    Explanations

    code elements and functions related to URLs and API interactions

    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
     пода
    -0.38
    ltk
    -0.37
    hon
    -0.35
    RefNanny
    -0.35
     económico
    -0.34
    ubarak
    -0.34
     fér
    -0.33
     delicacy
    -0.33
    ینده
    -0.33
     Nieder
    -0.33
    POSITIVE LOGITS
     URL
    2.09
     url
    2.08
    URL
    1.78
     Url
    1.77
    url
    1.77
    Url
    1.70
     URLs
    1.66
     urls
    1.54
    setUrl
    1.38
    getUrl
    1.34
    Activations Density 0.654%

    No Known Activations