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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1740
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate belonging or association

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewFeatures
    -0.77
    TestingModule
    -0.74
    ValueGenerated
    -0.73
     Seeder
    -0.73
     оригіналу
    -0.72
    MigrationBuilder
    -0.72
    ukone
    -0.68
    slidesToShow
    -0.68
     Pristupljeno
    -0.68
    ImageContext
    -0.66
    POSITIVE LOGITS
     belong
    3.12
     belongs
    3.01
     belonged
    2.77
    belong
    2.72
     belonging
    2.58
     Belong
    2.56
    belongs
    2.34
     pertenece
    1.95
     appartiennent
    1.88
     appartient
    1.88
    Activations Density 0.041%

    No Known Activations