© 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. 33-GEMMASCOPE-RES-16K
    11. 8107
    Prev
    Next
    INDEX
    Explanations

    structural or syntax-related elements in code, such as parameters, values, and key declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.70
     propOrder
    -0.69
     CreateTagHelper
    -0.67
    KommentareTeilen
    -0.67
     autorytatywna
    -0.65
    ',
    -0.60
    المشاركات
    -0.60
    
    -0.58
    ThroughAttribute
    -0.58
    iments
    -0.57
    POSITIVE LOGITS
     vectorielle
    0.44
     Fotografía
    0.42
     financiación
    0.39
     dictadura
    0.39
     Turquía
    0.36
     liknande
    0.34
     finanzas
    0.34
     fotográfica
    0.33
     féminine
    0.33
     similaires
    0.33
    Activations Density 0.501%

    No Known Activations