© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8466
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols related to sequences and limits

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

    mathematical variables and notation, particularly when involving subscripts and numerical indices.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    цездатний
    -0.69
     lenker
    -0.64
    AddTagHelper
    -0.59
     BorderSide
    -0.58
    出版年
    -0.58
    Хьажоргаш
    -0.58
    awtextra
    -0.57
    rungsseite
    -0.57
    expandindo
    -0.56
    المكان
    -0.55
    POSITIVE LOGITS
    long
    0.37
     tiré
    0.35
     tendre
    0.34
     Walden
    0.34
     infal
    0.33
     long
    0.33
    impl
    0.31
     lotes
    0.30
     copias
    0.30
    HttpResponse
    0.30
    Activations Density 1.043%

    No Known Activations