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

    Neuronpedia

    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. 15-GEMMASCOPE-RES-16K
    11. 3608
    Prev
    Next
    INDEX
    Explanations

    references to notable buildings or architectural structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.68
     mobilité
    -0.59
    الإنجليزية
    -0.55
    printStackTrace
    -0.54
     électro
    -0.52
    UnsafeEnabled
    -0.51
    WriteTagHelper
    -0.51
    ffichage
    -0.51
    TSCA
    -0.50
    bindParam
    -0.49
    POSITIVE LOGITS
     buildings
    1.10
     building
    0.93
     houses
    0.90
     structure
    0.90
     structures
    0.85
    buildings
    0.84
     Buildings
    0.84
    edificio
    0.81
     gebouw
    0.80
     mansion
    0.79
    Activations Density 0.325%

    No Known Activations