© 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. 36-GEMMASCOPE-RES-16K
    6. 11367
    Prev
    Next
    INDEX
    Explanations

    hyperlinks and references to software components, particularly related to Docker and programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <tbody>
    -0.32
     giustizia
    -0.32
    einander
    -0.32
     varandra
    -0.31
     industriels
    -0.29
    AppUser
    -0.28
     ح
    -0.28
    grow
    -0.28
     catálogo
    -0.27
     tomba
    -0.27
    POSITIVE LOGITS
    httphttps
    0.81
    AndEndTag
    0.76
    出版年
    0.73
     Taktlose
    0.73
    ConstraintMaker
    0.73
    \{\\
    0.69
    ValueStyle
    0.66
     ExecuteAsync
    0.64
    ImageContext
    0.63
     AssemblyTitle
    0.62
    Activations Density 0.167%

    No Known Activations