© 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. 3-GEMMASCOPE-RES-16K
    11. 6126
    Prev
    Next
    INDEX
    Explanations

    references and citations in academic and scientific writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shund
    -0.39
     clam
    -0.38
     surla
    -0.38
    temi
    -0.38
    enschein
    -0.38
     '\\;'
    -0.38
    paio
    -0.37
     censiti
    -0.37
     Chassis
    -0.37
     disponibilités
    -0.36
    POSITIVE LOGITS
    PhysRev
    0.77
     Journal
    0.70
     ProtoMessage
    0.66
     Acta
    0.63
     Appl
    0.58
    Journal
    0.57
     DataLoader
    0.56
    ⓧ
    0.56
     Sci
    0.55
     Lett
    0.53
    Activations Density 1.299%

    No Known Activations