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. 6-GEMMASCOPE-RES-16K
    6. 346
    Prev
    Next
    INDEX
    Explanations

    references to serving food

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -0.59
     viewDidLoad
    -0.55
     MonoBehaviour
    -0.53
     ©️
    -0.53
    autoreleasepool
    -0.52
    execSQL
    -0.51
     发表于
    -0.51
    kuuta
    -0.51
     Pencil
    -0.51
    pencil
    -0.50
    POSITIVE LOGITS
     Presenting
    0.91
     presenting
    0.90
    Presenting
    0.89
     presentation
    0.84
     Presentation
    0.81
     displaying
    0.78
     presenters
    0.77
     presentations
    0.76
     presenter
    0.75
     Delivered
    0.75
    Activations Density 0.560%

    No Known Activations