© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13520
    Prev
    Next
    INDEX
    Explanations

    declarations of public classes and their characteristics in a codebase

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

    "public class" or "class" keywords

    np_acts-logits-general · gemini-2.0-flash

    public class declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    rawDesc
    -0.57
    SceneManagement
    -0.50
     resourceCulture
    -0.48
    addCriterion
    -0.47
    PickerController
    -0.45
    IntoConstraints
    -0.45
    ScopeManager
    -0.44
    TokenNameDOT
    -0.43
     Мексичка
    -0.43
    AsUp
    -0.43
    POSITIVE LOGITS
     Sleeve
    0.48
     sleeve
    0.48
    Sleeve
    0.47
     odonto
    0.47
    もしろ
    0.46
    artisan
    0.46
     umpire
    0.45
    ことができました
    0.44
    structure
    0.44
     Muster
    0.43
    Activations Density 0.018%

    No Known Activations