© 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. 36-GEMMASCOPE-RES-16K
    11. 16185
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs, data structures, and mathematical functions

    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
     autorytatywna
    -0.92
    IsMutable
    -0.70
    parsedMessage
    -0.62
     تضيفلها
    -0.60
    IVEREF
    -0.58
    WriteAttribute
    -0.57
    BufferException
    -0.57
     دیکھیے
    -0.56
    رشف
    -0.55
    rrggbb
    -0.54
    POSITIVE LOGITS
     -
    1.20
     minus
    1.15
     –
    1.09
     −
    1.09
     $-
    0.92
     $-$
    0.89
    −
    0.87
    ()-
    0.85
     —
    0.85
    －
    0.82
    Activations Density 1.836%

    No Known Activations