© 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. 10-GEMMASCOPE-RES-16K
    6. 15902
    Prev
    Next
    INDEX
    Explanations

    sections or structural markers within documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.69
     coucher
    -0.56
    AnimationsModule
    -0.48
    aarrggbb
    -0.47
    issionais
    -0.46
    pousada
    -0.45
    anniversaire
    -0.45
    Välislingid
    -0.44
     muñ
    -0.44
     tambi
    -0.44
    POSITIVE LOGITS
    section
    2.25
    subsection
    1.27
     section
    1.23
    Section
    1.20
    sections
    1.13
     Section
    1.08
     sections
    1.08
    subsubsection
    1.08
     Sections
    1.00
    Sections
    0.96
    Activations Density 0.015%

    No Known Activations