© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 16231
    Prev
    Next
    INDEX
    Explanations

    references to bra sizes and fitting issues

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

    sizes (small, medium, etc.)

    np_acts-logits-general · gemini-2.0-flash

    clothing sizes and fit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     daily
    -0.41
    saraba
    -0.38
     hồi
    -0.36
    早速
    -0.35
    Prijs
    -0.35
    (&$
    -0.35
    Situation
    -0.34
    おもちゃ
    -0.34
    '][]
    -0.34
     ऐ
    -0.34
    POSITIVE LOGITS
     sizing
    0.54
    ViewFeatures
    0.54
     betweenstory
    0.54
     Sizing
    0.54
    sizeCache
    0.52
     tailles
    0.49
    ंदीखरीदारी
    0.48
     NSCoder
    0.46
    Sizing
    0.43
     Drapeau
    0.42
    Activations Density 0.051%

    No Known Activations