© 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. 4-GEMMASCOPE-RES-16K
    11. 1320
    Prev
    Next
    INDEX
    Explanations

    instances of the word "build" in various contexts related to project configuration and construction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    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
    -0.74
    ThroughAttribute
    -0.73
     asyncio
    -0.72
    UserScript
    -0.70
    بوابة
    -0.69
     defaultstate
    -0.69
    posedge
    -0.66
    XmlAccessorType
    -0.62
     /\.
    -0.62
     Insets
    -0.62
    POSITIVE LOGITS
    build
    1.93
     Build
    1.81
    Build
    1.79
     build
    1.67
     BUILD
    1.55
    BUILD
    1.46
     builds
    1.25
    Builds
    1.18
     Builds
    1.16
     buil
    1.16
    Activations Density 0.078%

    No Known Activations