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. 3-GEMMASCOPE-RES-16K
    6. 11130
    Prev
    Next
    INDEX
    Explanations

    elements related to view controllers and user interface components in programming documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.78
    SourceChecksum
    -0.77
    enumi
    -0.76
    bcryptjs
    -0.74
    Sami
    -0.72
     Bradbury
    -0.71
    ьаж
    -0.68
    /******/
    -0.67
     estimés
    -0.66
    帖最后由
    -0.66
    POSITIVE LOGITS
    ViewController
    3.51
     ViewController
    2.21
    UIViewController
    1.50
    viewController
    1.45
     UIKit
    1.22
    viewDidLoad
    1.18
     viewDidLoad
    1.06
    UITableView
    0.95
     XCTest
    0.93
    PickerController
    0.90
    Activations Density 0.055%

    No Known Activations