Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13435
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "build" in various forms within programming or API documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.79
    tanleria
    -0.71
     building
    -0.71
    issory
    -0.69
     NgModule
    -0.67
    ViewFeatures
    -0.66
    enterOuterAlt
    -0.66
    المكان
    -0.65
     Мексичка
    -0.63
    nahm
    -0.62
    POSITIVE LOGITS
    build
    1.36
    Build
    1.07
     Build
    0.84
     CURIAM
    0.57
     presente
    0.55
    Compile
    0.54
     viewDidLoad
    0.52
    sigs
    0.50
     macular
    0.48
    日閲覧
    0.48
    Activations Density 0.266%

    No Known Activations