© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 6736
    Prev
    Next
    INDEX
    Explanations

    instances of the access modifier "private" in code snippets

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

    instances of access modifiers, specifically "private"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Poppy
    -0.71
    GraphicsUnit
    -0.67
     typelib
    -0.65
     poppy
    -0.65
    waitKey
    -0.64
    =="
    -0.64
     poppies
    -0.63
    mphony
    -0.63
    torio
    -0.62
     mosque
    -0.62
    POSITIVE LOGITS
    private
    1.70
     private
    1.21
     Private
    1.07
    Private
    0.98
    PRIVATE
    0.97
     PRIVATE
    0.91
     privat
    0.86
     nonatomic
    0.79
     privado
    0.78
     privadas
    0.74
    Activations Density 0.026%

    No Known Activations