© 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. 3-GEMMASCOPE-RES-16K
    6. 6837
    Prev
    Next
    INDEX
    Explanations

    references to data byte sizes

    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
     propOrder
    -0.62
     NSCoder
    -0.57
    InjectAttribute
    -0.54
     Roskov
    -0.47
     Belts
    -0.47
     שוליים
    -0.46
     <>",
    -0.45
    invokeLater
    -0.44
     оригіналу
    -0.44
     puder
    -0.43
    POSITIVE LOGITS
     bytes
    1.21
     byte
    1.10
    bytes
    1.05
    Byte
    1.04
     Byte
    1.01
    Bytes
    1.00
     Bytes
    0.96
    BYTES
    0.78
    byte
    0.77
     bite
    0.69
    Activations Density 0.127%

    No Known Activations