© 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. 1-GEMMASCOPE-RES-16K
    6. 9943
    Prev
    Next
    INDEX
    Explanations

    words related to construction, assembly, or development processes

    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
     smuggled
    -0.61
    XmlAccessorType
    -0.60
     smaak
    -0.58
    getKeyCode
    -0.56
     tradizione
    -0.56
    anoma
    -0.56
     sécher
    -0.56
     laiton
    -0.56
     ocorrer
    -0.55
     saveurs
    -0.55
    POSITIVE LOGITS
     building
    4.07
     Building
    3.61
    building
    3.61
    Building
    3.54
     BUILDING
    3.18
    BUILDING
    3.06
     build
    2.88
    build
    2.67
     Build
    2.65
     builds
    2.58
    Activations Density 0.121%

    No Known Activations