© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 5840
    Prev
    Next
    INDEX
    Explanations

    components related to web reporting and case studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.71
     autorytatywna
    -0.60
    
    -0.60
    Diweddarwch
    -0.54
    exitRule
    -0.53
     intptr
    -0.50
    İstinadlar
    -0.50
    Erreferentziak
    -0.49
    Personendaten
    -0.48
    Jegyzetek
    -0.47
    POSITIVE LOGITS
     report
    3.73
    report
    3.28
     reports
    3.27
     Report
    3.20
    Report
    3.13
     REPORT
    3.06
     Reports
    2.97
    reports
    2.91
     reporting
    2.86
    REPORT
    2.83
    Activations Density 0.834%

    No Known Activations