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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-16K
    6. 15518
    Prev
    Next
    INDEX
    Explanations

    classes and data structures related to serialization and generic types in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.66
    IonicModule
    -0.61
    cookieParser
    -0.60
    CreateMap
    -0.56
     Zey
    -0.56
     Comédie
    -0.53
    issipp
    -0.53
     '{@
    -0.53
     Egli
    -0.53
     Isma
    -0.53
    POSITIVE LOGITS
    onedDateTime
    0.66
     EconPapers
    0.63
    RegistryLite
    0.62
    inė
    0.59
    []
    0.58
    peu
    0.57
    endola
    0.54
    BufferException
    0.54
    RectangleBorder
    0.53
    ánto
    0.53
    Activations Density 0.304%

    No Known Activations