© 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. 11-GEMMASCOPE-RES-16K
    11. 5372
    Prev
    Next
    INDEX
    Explanations

    specific references to entities involved in legal or formal proceedings

    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
    
    -0.68
    SequentialGroup
    -0.53
    InjectAttribute
    -0.50
    ParseTree
    -0.49
    Vidite
    -0.48
    duate
    -0.47
    ecy
    -0.47
    NewReader
    -0.47
    pell
    -0.47
     surla
    -0.46
    POSITIVE LOGITS
     oposición
    0.36
    خواندن
    0.36
     jsPsych
    0.33
     Gewerks
    0.33
    addCriterion
    0.32
     neumáticos
    0.31
    mintaan
    0.30
     autorités
    0.30
     Privacidad
    0.30
     Verantwort
    0.30
    Activations Density 1.013%

    No Known Activations