© 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. 898
    Prev
    Next
    INDEX
    Explanations

    keywords related to access modifiers and function definitions in programming

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

    Code related to access modifiers

    np_acts-logits-general · gemini-2.0-flash

    protected keyword in code

    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
     ***!
    -0.74
    ArrowToggle
    -0.67
    Tikang
    -0.63
    awtextra
    -0.59
    isEmail
    -0.57
    
    -0.55
    Portail
    -0.55
     getItemId
    -0.54
     surla
    -0.54
    -------------</
    -0.53
    POSITIVE LOGITS
    protected
    1.13
     protected
    0.75
     protect
    0.67
    protect
    0.65
     PROTECT
    0.57
    Protected
    0.56
     protecting
    0.56
     protection
    0.54
     Protected
    0.54
    PROTECT
    0.53
    Activations Density 0.034%

    No Known Activations