© 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 EvalsExportsAPI 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. 14956
    Prev
    Next
    INDEX
    Explanations

    chemical compounds and their classifications

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

    References/citations within square brackets

    np_acts-logits-general · gemini-2.0-flash

    numbers and symbols

    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
     мәкал
    -0.80
    ագրություններ
    -0.68
    #
    -0.66
     kasarigan
    -0.63
     AssemblyTitle
    -0.63
     autorytatywna
    -0.62
    Transkript
    -0.60
     queſta
    -0.59
    Parcelize
    -0.59
    出版年
    -0.59
    POSITIVE LOGITS
     SUDOC
    0.31
    XmlIgnore
    0.31
     casque
    0.29
    Tazama
    0.29
     Савез
    0.28
     Palestina
    0.28
     Statt
    0.27
     bonjour
    0.27
     corrientes
    0.27
     paire
    0.27
    Activations Density 0.724%

    No Known Activations