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. 2564
    Prev
    Next
    INDEX
    Explanations

    information related to artistic institutions and exhibits

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

    museums or exhibitions

    np_acts-logits-general · gemini-2.0-flash

    museums and their collections

    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
    IntoConstraints
    -0.77
    ctomy
    -0.52
     AssemblyCulture
    -0.50
     albicans
    -0.50
    indd
    -0.49
     Untitled
    -0.49
     Strava
    -0.48
     bridesmaid
    -0.47
     MacBook
    -0.46
    grids
    -0.45
    POSITIVE LOGITS
     museum
    1.93
     Museum
    1.71
     museums
    1.59
    Museum
    1.51
    museum
    1.50
     exhibits
    1.43
     museo
    1.42
     MUSEUM
    1.41
     exhibit
    1.28
     Museums
    1.28
    Activations Density 0.142%

    No Known Activations