© 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 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. 2666
    Prev
    Next
    INDEX
    Explanations

    references to error handling and data structure creation in programming code

    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
    ConstraintMaker
    -0.70
     ब्रेकडाउन
    -0.64
     snippetHide
    -0.63
    WebVitals
    -0.63
    şört
    -0.61
     ویکی‌آمباردا
    -0.61
     חיצוניים
    -0.60
     resourceCulture
    -0.59
     שוליים
    -0.58
     '\\;'
    -0.58
    POSITIVE LOGITS
     Ordnung
    0.32
     Karlsson
    0.32
     Duncan
    0.32
     bezeichneter
    0.30
    нк
    0.30
     Jensen
    0.30
     Nav
    0.30
     Craig
    0.29
     Asoci
    0.29
    archiviato
    0.29
    Activations Density 0.393%

    No Known Activations