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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4268
    Prev
    Next
    INDEX
    Explanations

    references to the character "Mario" and associated terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Geplaatst
    -0.66
    stddef
    -0.63
    runApp
    -0.62
    spesies
    -0.61
    oredCriteria
    -0.59
     Tatsache
    -0.58
     ajoutez
    -0.58
    verifier
    -0.57
    quele
    -0.56
     useStyles
    -0.56
    POSITIVE LOGITS
    NavController
    0.74
    fulness
    0.74
    ropractic
    0.70
     Flags
    0.68
    `${
    0.68
    Extinguishing
    0.67
    ►
    0.66
    reactstrap
    0.65
     ESE
    0.64
    flags
    0.64
    Activations Density 0.508%

    No Known Activations