Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 6-GEMMASCOPE-RES-16K
    6. 488
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "private" in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poppies
    -0.78
     Poppy
    -0.76
     acorns
    -0.75
    =="
    -0.75
     officiellement
    -0.73
    ulemon
    -0.70
    Morfologia
    -0.69
    oredCriteria
    -0.68
     Maureen
    -0.68
     culturelle
    -0.68
    POSITIVE LOGITS
    private
    1.88
     private
    1.57
     Private
    1.51
    Private
    1.41
    PRIVATE
    1.34
     PRIVATE
    1.27
     privat
    1.18
     Privat
    1.14
     privada
    1.08
     privaten
    1.08
    Activations Density 0.025%

    No Known Activations