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. 21-GEMMASCOPE-RES-16K
    6. 6547
    Prev
    Next
    INDEX
    Explanations

    references to food and catering options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minimise
    -0.59
     incenti
    -0.56
     connect
    -0.55
     prioritise
    -0.54
    testng
    -0.54
     connects
    -0.54
     neighbourhoods
    -0.53
     renta
    -0.52
     optimise
    -0.51
    labour
    -0.50
    POSITIVE LOGITS
    DockStyle
    0.71
     تضيفلها
    0.69
     Meksiku
    0.68
    DoubleQuotes
    0.66
    horabuena
    0.63
    Portale
    0.62
    ^(@)
    0.62
    Poloha
    0.62
     pinulongan
    0.61
    excellent
    0.60
    Activations Density 0.042%

    No Known Activations