© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 10479
    Prev
    Next
    INDEX
    Explanations

    references to model-related content and fashion events

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

    after "the," "unk," or ","

    np_acts-logits-general · gemini-2.0-flash

    runway and modeling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.58
    TextWatcher
    -0.57
     autorytatywna
    -0.51
    RefNanny
    -0.50
     nahilalakip
    -0.50
    Lähteet
    -0.49
    ειτουργ
    -0.48
    tagHelperRunner
    -0.47
    webElementXpaths
    -0.46
     StatefulWidget
    -0.46
    POSITIVE LOGITS
     catwalk
    0.87
     models
    0.85
     modeling
    0.84
     runway
    0.79
    models
    0.78
     model
    0.78
     modelling
    0.78
     Models
    0.77
     beauty
    0.77
     fashion
    0.77
    Activations Density 0.076%

    No Known Activations