© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 11753
    Prev
    Next
    INDEX
    Explanations

    phrases related to constructing or establishing something

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

    Tokens after the word "build" or "builds"

    np_acts-logits-general · gemini-2.0-flash

    build

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doulou
    -0.80
     MotionEvent
    -0.74
     variés
    -0.68
     thermique
    -0.65
     pitié
    -0.64
     snoring
    -0.64
     argint
    -0.63
     préfé
    -0.63
     Chromatography
    -0.61
    RADIUS
    -0.61
    POSITIVE LOGITS
    BUILD
    1.50
     BUILD
    1.44
     build
    1.43
    build
    1.37
     builds
    1.37
     Build
    1.35
    builds
    1.33
     built
    1.25
    Build
    1.24
     building
    1.24
    Activations Density 0.114%

    No Known Activations