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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15501
    Prev
    Next
    INDEX
    Explanations

    instances of JPA repository interfaces and their implementations in the context of Spring Boot applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tonsoft
    -0.55
    IVEREF
    -0.53
     المعيارى
    -0.43
    anniversaire
    -0.42
    WithIOException
    -0.42
    UnusedPrivate
    -0.42
     servos
    -0.40
     procesador
    -0.40
     broadcasters
    -0.40
     CanadaChoose
    -0.40
    POSITIVE LOGITS
    UserRepository
    0.73
    Repository
    0.70
     JpaRepository
    0.68
     repository
    0.67
     Repository
    0.66
    JpaRepository
    0.65
     UserRepository
    0.64
    repository
    0.64
     UserDao
    0.63
    UserDao
    0.58
    Activations Density 0.026%

    No Known Activations