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. 11-GEMMASCOPE-RES-16K
    6. 6343
    Prev
    Next
    INDEX
    Explanations

    references to household appliances and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '])->
    -0.82
    gdx
    -0.73
    ](#
    -0.66
    lipop
    -0.65
     auttaa
    -0.63
     فريبيس
    -0.61
    querade
    -0.60
    IntoConstraints
    -0.60
    rungsseite
    -0.60
    AlterField
    -0.59
    POSITIVE LOGITS
     appliances
    0.91
     refrigerator
    0.83
     refrigerators
    0.77
     Appliances
    0.73
     Refrigerator
    0.73
     appliance
    0.72
    domésticos
    0.69
     oven
    0.68
     dishwasher
    0.66
     ovens
    0.66
    Activations Density 0.104%

    No Known Activations