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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 8420
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and relationships related to structures and properties of partitions and graphs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betale
    -0.49
    QPushButton
    -0.48
     paiement
    -0.47
    OuterClass
    -0.47
     supplémentaire
    -0.47
     ansatte
    -0.46
    CollectionView
    -0.45
     considérons
    -0.45
     projectiles
    -0.45
     przep
    -0.45
    POSITIVE LOGITS
    npos
    0.69
    rrggbb
    0.63
    setVerticalGroup
    0.63
    المناصب
    0.62
    SharedCtor
    0.62
    InsertCommand
    0.62
     يتيمه
    0.61
    elemField
    0.60
    ModelAdmin
    0.60
    EndGlobalSection
    0.60
    Activations Density 1.178%

    No Known Activations