© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1204
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to web services and API interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code-related terms, often involving VPN or requests

    np_acts-logits-general · gemini-2.0-flash

    vpnSite parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Nazionale
    -0.65
    Sucesor
    -0.60
    AndEndTag
    -0.60
    InjectAttribute
    -0.57
     نخ
    -0.55
     Erişim
    -0.54
     définiti
    -0.54
     Still
    -0.54
     Resultados
    -0.53
    memoized
    -0.53
    POSITIVE LOGITS
    RequestBody
    1.01
     FormData
    0.88
     body
    0.87
     payload
    0.79
    body
    0.79
    payload
    0.78
    requestBody
    0.74
     formData
    0.73
     Body
    0.72
    formData
    0.72
    Activations Density 0.110%

    No Known Activations