© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6508
    Prev
    Next
    INDEX
    Explanations

    phrases related to architectural details and historical buildings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Architectural construction and building descriptions

    np_acts-logits-general · gemini-2.0-flash

    buildings built or designed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ंदीखरीदारी
    -0.37
    olah
    -0.36
     rela
    -0.35
     Zust
    -0.34
     Tiefen
    -0.34
    Chham
    -0.34
    spaceBetween
    -0.33
    refour
    -0.33
    Werdegang
    -0.33
     lái
    -0.33
    POSITIVE LOGITS
     architectural
    1.16
     architect
    1.12
     architecture
    1.05
     buildings
    1.05
    建築
    1.03
    architect
    1.00
     building
    0.99
     architects
    0.98
     arquitectura
    0.97
     arquitect
    0.96
    Activations Density 0.279%

    No Known Activations