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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9456
    Prev
    Next
    INDEX
    Explanations

    technical vocabulary related to chemical processes and materials synthesis

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

    Nanoparticles containing silver (Ag)

    np_acts-logits-general · gemini-2.0-flash

    prepare silver nanoparticles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mbangkan
    -0.47
    ibus
    -0.41
    мм
    -0.39
     subscribers
    -0.39
    migrationBuilder
    -0.38
    GCM
    -0.38
    bura
    -0.37
    Gemeinden
    -0.37
     proyec
    -0.37
     kommune
    -0.36
    POSITIVE LOGITS
     '\\;'
    0.84
    ftagPool
    0.82
    קישורים
    0.78
     lenker
    0.77
    adpleegd
    0.74
     nanop
    0.72
     surface
    0.72
     colloidal
    0.71
     adsor
    0.70
    ſelf
    0.70
    Activations Density 1.161%

    No Known Activations