© 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. 22-GEMMASCOPE-RES-16K
    6. 6422
    Prev
    Next
    INDEX
    Explanations

    mechanical components and their interactions in engineering contexts

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

    Mechanical components or parts

    np_acts-logits-general · gemini-2.0-flash

    mechanical and electrical components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IndentedString
    -0.78
    makeConstraints
    -0.75
     intptr
    -0.75
    FontOfSize
    -0.72
     disambiguazione
    -0.69
    AutoresizingMask
    -0.67
    readystatechange
    -0.67
     EdgeInsets
    -0.65
     >=",
    -0.65
    setVerticalGroup
    -0.64
    POSITIVE LOGITS
     plate
    0.82
     assembly
    0.74
     area
    0.73
     assemblies
    0.68
    plate
    0.66
     plates
    0.66
     assy
    0.63
     cup
    0.60
     portion
    0.59
     guards
    0.56
    Activations Density 0.814%

    No Known Activations