© 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. 37-GEMMASCOPE-RES-16K
    11. 4518
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and logical conditions within expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HasFactory
    -0.61
    setVerticalGroup
    -0.57
     Winaray
    -0.56
     AssemblyCulture
    -0.56
     ExecuteAsync
    -0.56
    AndEndTag
    -0.55
     autorytatywna
    -0.51
     Taktlose
    -0.50
    RTCK
    -0.50
     propOrder
    -0.49
    POSITIVE LOGITS
     O
    3.13
    O
    2.31
     o
    2.20
     о
    1.54
     О
    1.49
     ओ
    1.43
    Ｏ
    1.32
    О
    1.27
     ο
    1.21
     Ο
    1.13
    Activations Density 1.068%

    No Known Activations