© 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. 37-GEMMASCOPE-RES-16K
    6. 3543
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data handling and processing

    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
     CreateTagHelper
    -0.94
    SharedCtor
    -0.82
    httphttps
    -0.77
    __":
    
    -0.75
    RegressionTest
    -0.73
     jSON
    -0.72
     EconPapers
    -0.69
     intptr
    -0.69
    zzleHttp
    -0.69
    __':
    
    -0.69
    POSITIVE LOGITS
    siapkan
    0.36
    ِّف
    0.34
     Gefahr
    0.32
     Vergnügen
    0.31
     Wochenende
    0.31
    と呼ばれる
    0.31
    ándonos
    0.31
     Geschlecht
    0.30
     tradicionales
    0.30
    tagez
    0.29
    Activations Density 2.475%

    No Known Activations