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. 8-GEMMASCOPE-RES-16K
    6. 14831
    Prev
    Next
    INDEX
    Explanations

    references to database-related concepts and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OnInit
    -0.71
     CGSize
    -0.67
    Geplaatst
    -0.63
    serviceWorker
    -0.62
     AppComponent
    -0.60
    geslacht
    -0.60
     CGPoint
    -0.60
    ExtendWith
    -0.59
     Afternoon
    -0.59
     entertain
    -0.59
    POSITIVE LOGITS
    EntityFramework
    1.08
     sqlite
    0.97
    SqlClient
    0.96
     database
    0.87
    sqlite
    0.85
    mysql
    0.85
    sequelize
    0.84
    quelize
    0.83
    SQLite
    0.82
     sqlalchemy
    0.82
    Activations Density 0.150%

    No Known Activations