© 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. 16133
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and formatting elements in equations and expressions

    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
    grid
    -0.47
    guild
    -0.43
    guid
    -0.39
    glyph
    -0.37
    guard
    -0.36
    gateway
    -0.36
    guess
    -0.35
    gallery
    -0.35
    gauge
    -0.35
    grant
    -0.32
    POSITIVE LOGITS
     G
    2.86
     g
    2.19
    G
    2.17
    Ｇ
    1.45
     گ
    1.38
     Г
    1.34
    g
    1.25
     ग
    1.23
     г
    1.21
     ג
    1.16
    Activations Density 1.295%

    No Known Activations