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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 4553
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to warranties and guarantees

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ExecuteAsync
    -1.03
     initComponents
    -0.95
     Theſe
    -0.91
    AnchorStyles
    -0.89
     ModelExpression
    -0.87
     pleaſure
    -0.85
     مشين
    -0.84
     跳转至
    -0.83
    didSet
    -0.81
    BeginContext
    -0.80
    POSITIVE LOGITS
     warranty
    1.27
     warranties
    1.15
    warranty
    1.13
     WARRANTY
    1.06
    Warranty
    1.06
     Warranty
    1.05
    WARRANTY
    0.84
     WARRANTIES
    0.79
     warran
    0.79
     garantie
    0.74
    Activations Density 0.127%

    No Known Activations