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. 16-GEMMASCOPE-RES-16K
    6. 1697
    Prev
    Next
    INDEX
    Explanations

    references to the term "private" in various contexts, including private individuals, meetings, security, and companies

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

    Following the word "private"

    np_acts-logits-general · gemini-2.0-flash

    private context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.85
    FormTagHelper
    -0.67
     Citron
    -0.67
     onOptions
    -0.66
    OrEqual
    -0.63
    =="
    -0.63
     Gaston
    -0.62
    dataflow
    -0.61
     ++)
    -0.60
    ))\
    -0.60
    POSITIVE LOGITS
    PRIVATE
    1.07
    Private
    1.04
     Private
    1.02
     private
    1.01
     PRIVATE
    0.94
     privada
    0.91
     privados
    0.91
     Privat
    0.89
     privado
    0.88
     privato
    0.87
    Activations Density 0.065%

    No Known Activations