© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3226
    Prev
    Next
    INDEX
    Explanations

    names of materials and substances

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

    Materials (metal, wood, glass, etc.)

    np_acts-logits-general · gemini-2.0-flash

    materials and substances

    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
     للاسماء
    -0.61
    unanje
    -0.54
     الحره
    -0.53
    Cyfeiriadau
    -0.50
    Примітки
    -0.47
     fiscales
    -0.47
     traseiro
    -0.47
    getWriter
    -0.47
     drenaje
    -0.47
    ieteur
    -0.47
    POSITIVE LOGITS
     metal
    1.46
     wood
    1.45
     steel
    1.43
     plastic
    1.35
     metals
    1.24
     aluminum
    1.24
     glass
    1.22
     plastics
    1.21
     leather
    1.21
    metal
    1.19
    Activations Density 0.676%

    No Known Activations