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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 12644
    Prev
    Next
    INDEX
    Explanations

    references to sources and citations of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tadır
    -0.53
    CppCodeGen
    -0.52
     насељу
    -0.50
    esterday
    -0.45
     للتو
    -0.45
    bindParam
    -0.43
     numériques
    -0.43
     serons
    -0.42
     Waray
    -0.41
    Stored
    -0.41
    POSITIVE LOGITS
    IUrlHelper
    0.79
    ########.
    0.76
    aarrggbb
    0.69
     AssemblyCompany
    0.68
     ویکی‌پدیای
    0.62
     snippetHide
    0.58
    oredCriteria
    0.58
     pinulongan
    0.56
    
    0.56
    ProductService
    0.55
    Activations Density 0.288%

    No Known Activations