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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15036
    Prev
    Next
    INDEX
    Explanations

    references to processes involving HTTP requests and data fetching

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.83
     pinulongan
    -0.59
    keyColumn
    -0.57
    Palmar
    -0.52
    Subviews
    -0.52
     StatelessWidget
    -0.51
    visning
    -0.50
    versary
    -0.50
     ролях
    -0.49
    μερα
    -0.48
    POSITIVE LOGITS
    http
    1.00
     axios
    1.00
     request
    0.98
     fetch
    0.98
    axios
    0.96
    fetch
    0.95
     http
    0.94
     requests
    0.92
     HTTP
    0.89
    请求
    0.88
    Activations Density 0.230%

    No Known Activations