© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 4022
    Prev
    Next
    INDEX
    Explanations

    links and URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    URLs (HTTP/HTTPS)

    np_acts-logits-general · gemini-2.0-flash

    urls starting with http or https

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.80
     XCTest
    -0.75
    RenderAtEndOf
    -0.68
    Xna
    -0.68
    تقاوى
    -0.68
     onCreateView
    -0.65
    SceneManagement
    -0.65
    viewDidLoad
    -0.64
     CreateTagHelper
    -0.63
    ScopeManager
    -0.61
    POSITIVE LOGITS
    ://
    0.53
    nloa
    0.51
     محفوظة
    0.48
     esterni
    0.45
    EndGlobalSection
    0.43
    
    0.42
    ArrowToggle
    0.42
     FormsModule
    0.41
    扩展
    0.40
     War
    0.40
    Activations Density 0.080%

    No Known Activations