© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 11306
    Prev
    Next
    INDEX
    Explanations

    elements related to programming concepts and structures, especially in coding syntax and declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.81
    "]);
    -0.71
    pexpr
    -0.67
     LoginPage
    -0.67
    клопе
    -0.67
    _));
    -0.66
    bulaire
    -0.66
     DbSet
    -0.65
     الرخصة
    -0.65
    ")){
    -0.65
    POSITIVE LOGITS
     back
    0.56
    Erreferentziak
    0.49
    Back
    0.49
     arrière
    0.44
    ruptedException
    0.44
    TAWA
    0.43
    コール
    0.42
     وسلم
    0.42
     okuyayım
    0.42
    back
    0.41
    Activations Density 0.229%

    No Known Activations