© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 183
    Prev
    Next
    INDEX
    Explanations

    references to auto or automatic processes related to REST APIs and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anfitrión
    -0.98
    URLException
    -0.96
     méri
    -0.88
     grecque
    -0.88
    contentLoaded
    -0.87
     Мексичка
    -0.86
     Réponses
    -0.86
    aarrggbb
    -0.85
    jspx
    -0.85
    Personensuche
    -0.84
    POSITIVE LOGITS
     Auto
    2.02
     auto
    1.99
     AUTO
    1.98
    Auto
    1.85
    auto
    1.84
    AUTO
    1.74
    setAuto
    1.38
     autos
    1.34
    autos
    1.24
     Autos
    1.24
    Activations Density 0.039%

    No Known Activations