© 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. 10-GEMMASCOPE-RES-16K
    11. 6946
    Prev
    Next
    INDEX
    Explanations

    terms related to health initiatives and emergency response

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ouv
    -0.55
    ائق
    -0.52
    stdafx
    -0.52
    consume
    -0.50
    strconv
    -0.49
    zette
    -0.49
    ciale
    -0.49
     anteriore
    -0.49
    änomen
    -0.48
     Hebrew
    -0.48
    POSITIVE LOGITS
    AddTagHelper
    0.62
    LabelTagHelper
    0.62
    TagMode
    0.61
    errHandler
    0.60
     INTERESAR
    0.60
    __":
    0.56
     Walkover
    0.56
    Искәрмәләр
    0.55
     USAID
    0.54
     विश्वसनीयता
    0.54
    Activations Density 0.138%

    No Known Activations