Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 2239
    Prev
    Next
    INDEX
    Explanations

    occurrences of programming-related terms and references to online repositories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.68
     AssemblyCulture
    -0.66
    HORE
    -0.63
    ROIT
    -0.62
     Akismet
    -0.60
    verwijspagina
    -0.60
    initComponents
    -0.59
    Tē
    -0.58
    ViewImports
    -0.58
    رشف
    -0.57
    POSITIVE LOGITS
    føl
    0.59
     gustó
    0.55
    CodeAttribute
    0.53
    !!!!
    0.50
     szép
    0.49
     lovely
    0.47
     wonderful
    0.47
     společnost
    0.47
    TypedDataSet
    0.46
     AssemblyProduct
    0.45
    Activations Density 0.045%

    No Known Activations