© 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. 7994
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and concepts, particularly those associated with assembly, attributes, and event handling in .NET

    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
     intptr
    -0.46
     juos
    -0.43
     dalamnya
    -0.42
    MigrationBuilder
    -0.42
    IsMutable
    -0.42
    󠁴
    -0.40
    posedge
    -0.40
     بيها
    -0.40
     ditulis
    -0.39
    ArrowToggle
    -0.39
    POSITIVE LOGITS
    Diweddarwch
    0.57
     autorytatywna
    0.53
    webElementGuid
    0.51
    脚注の使い方
    0.50
     Craft
    0.49
     посу
    0.47
     ◄
    0.47
     Wray
    0.46
    resources
    0.45
    Craft
    0.45
    Activations Density 0.048%

    No Known Activations