© 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. 11-GEMMASCOPE-RES-16K
    6. 8718
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 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
    httphttps
    -0.50
     geweest
    -0.47
     насељу
    -0.46
     flyg
    -0.45
     Füßen
    -0.44
     szcze
    -0.44
     vacuna
    -0.44
    Décès
    -0.43
    有多少
    -0.43
     gehad
    -0.42
    POSITIVE LOGITS
     ExecuteAsync
    0.56
    AddHtmlAttribute
    0.55
    {}/
    0.53
    GOTREF
    0.47
    [][
    0.45
    UserController
    0.44
     ostavi
    0.44
    Dichlor
    0.42
    󠁴
    0.42
    wapV
    0.41
    Activations Density 0.897%

    No Known Activations