© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6150
    Prev
    Next
    INDEX
    Explanations

    phrases related to statistical adjustments and controlling for variables in analysis

    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
    ParallelGroup
    -0.44
    }{#
    -0.40
    CellValue
    -0.38
     пона
    -0.37
    GEBURTSDATUM
    -0.37
    曖昧さ回避
    -0.37
    
    -0.36
    Hochspringen
    -0.36
     really
    -0.35
    ']))
    -0.35
    POSITIVE LOGITS
    HtmlAttribute
    0.59
     excluding
    0.57
    excluding
    0.56
    Including
    0.56
     Including
    0.54
     учетом
    0.52
    cluding
    0.51
     subtracting
    0.51
     pinulongan
    0.50
     factoring
    0.50
    Activations Density 0.948%

    No Known Activations