© 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. 0-GEMMASCOPE-RES-16K
    11. 7060
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to case filings and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     be
    -0.87
     find
    -0.79
     know
    -0.77
     get
    -0.74
     choose
    -0.69
     think
    -0.69
     keep
    -0.69
     have
    -0.69
     take
    -0.69
     make
    -0.68
    POSITIVE LOGITS
     فريبيس
    0.63
    GTCX
    0.56
     Савезне
    0.51
    parsedMessage
    0.50
    WebVitals
    0.50
     Numerade
    0.47
     utafitiHapana
    0.47
     ویکی‌پدیای
    0.47
    msgTypes
    0.46
     Lightboxes
    0.44
    Activations Density 1.310%

    No Known Activations