© 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. 2-GEMMASCOPE-RES-16K
    11. 4358
    Prev
    Next
    INDEX
    Explanations

    references to buildings and construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XtraReports
    -0.80
     pitié
    -0.75
     parishes
    -0.74
    XmlAccessorType
    -0.73
    Rptr
    -0.71
     paroisse
    -0.71
     priestly
    -0.70
     yyr
    -0.70
    zwungen
    -0.69
     anglers
    -0.68
    POSITIVE LOGITS
     building
    3.70
     Building
    3.35
    building
    3.24
    Building
    3.22
     BUILDING
    2.94
    BUILDING
    2.76
     buildings
    2.44
     Buildings
    2.27
    buildings
    2.26
     Bldg
    2.21
    Activations Density 0.075%

    No Known Activations