© 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. 5833
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations related to limits, summations, and inequalities

    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
     invokingState
    -0.71
     AssemblyTitle
    -0.71
    IntoConstraints
    -0.67
    WaitGroup
    -0.63
    PostInfinity
    -0.62
     Normdatei
    -0.61
    MES
    -0.58
    parsedMessage
    -0.58
     AssemblyCompany
    -0.57
     виправивши
    -0.56
    POSITIVE LOGITS
     må
    0.50
     המ
    0.48
     murder
    0.47
     mı
    0.47
     million
    0.47
     mã
    0.46
     mẹ
    0.46
     manager
    0.45
     medel
    0.44
     muur
    0.43
    Activations Density 1.152%

    No Known Activations