© 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. 11-GEMMASCOPE-RES-16K
    11. 8810
    Prev
    Next
    INDEX
    Explanations

    references to principal components and analyses related to data and measurement techniques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jestic
    -0.83
    cohort
    -0.74
     dysplasia
    -0.73
     Moody
    -0.73
     Garn
    -0.72
    phous
    -0.72
     Marge
    -0.71
     مشين
    -0.71
     Duran
    -0.71
    rictive
    -0.70
    POSITIVE LOGITS
     RZ
    0.83
     Lala
    0.82
     RAL
    0.79
     PRINCIP
    0.78
     Principals
    0.76
    例句
    0.75
     principle
    0.74
     VIL
    0.73
     goog
    0.73
     principals
    0.73
    Activations Density 0.231%

    No Known Activations