© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7221
    Prev
    Next
    INDEX
    Explanations

    instances of the word "build" and its variations related to construction or creation

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

    the word "build" or "building"

    np_acts-logits-general · gemini-2.0-flash

    act of construction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionTypes
    -0.56
    CppMethod
    -0.56
     '{@
    -0.53
    Orsay
    -0.52
    reportWebVitals
    -0.51
    awaiter
    -0.51
    CodeAttribute
    -0.50
     TimeSpan
    -0.49
     respective
    -0.49
    pexpr
    -0.48
    POSITIVE LOGITS
     Build
    1.30
    Build
    1.27
    build
    1.23
     build
    1.23
     BUILD
    1.19
    BUILD
    1.05
     Built
    1.05
    Built
    1.05
    Building
    1.04
     builder
    1.02
    Activations Density 0.077%

    No Known Activations