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. 4663
    Prev
    Next
    INDEX
    Explanations

    references to artistic disciplines and practices

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

    Art installations and multimedia works

    np_acts-logits-general · gemini-2.0-flash

    installation, sculptural, video art

    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
     FetchType
    -0.74
    RectangleBorder
    -0.71
     Christendom
    -0.71
     touristique
    -0.70
     CreateTagHelper
    -0.67
    imetsu
    -0.67
     wikipagina
    -0.65
     supérieurs
    -0.65
     purpoſe
    -0.65
    MigrationBuilder
    -0.65
    POSITIVE LOGITS
     installation
    0.95
     installations
    0.83
     sculptural
    0.82
    installation
    0.79
     experimental
    0.78
     Installation
    0.71
    Installation
    0.69
     conceptually
    0.67
    install
    0.66
     works
    0.65
    Activations Density 0.303%

    No Known Activations