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. 5-GEMMASCOPE-RES-16K
    6. 11546
    Prev
    Next
    INDEX
    Explanations

    LaTeX document class declarations and parameters related to logging and nullable properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.81
    ientôt
    -0.72
    таратура
    -0.70
    mybatisplus
    -0.70
    addContainerGap
    -0.65
     initComponents
    -0.63
     OnInit
    -0.62
    TagHelpers
    -0.58
    makeConstraints
    -0.55
    tamanya
    -0.54
    POSITIVE LOGITS
    documentclass
    1.25
    nullable
    1.16
    TypedDataSet
    1.07
    appcompat
    0.96
    клопе
    0.76
    hadoop
    0.71
    bootstrapcdn
    0.70
    出版年
    0.64
     StatelessWidget
    0.63
    swagger
    0.63
    Activations Density 0.012%

    No Known Activations