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. 681
    Prev
    Next
    INDEX
    Explanations

    the usage of the word "the" 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 @ 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
    aarrggbb
    -0.62
    oneofs
    -0.59
     Obrador
    -0.55
    ToBounds
    -0.54
    XtraReports
    -0.54
    LabelTagHelper
    -0.51
     beginnetje
    -0.50
    queryInterface
    -0.47
     calculées
    -0.46
    WebElementEntity
    -0.45
    POSITIVE LOGITS
     forefront
    0.96
     beginning
    0.93
     outset
    0.89
     moment
    0.88
     end
    0.86
     start
    0.81
    beginning
    0.77
     bottom
    0.75
     heart
    0.74
     helm
    0.73
    Activations Density 0.142%

    No Known Activations