© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 15849
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, specifically focusing on "Father" and "Queen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.71
     fièvre
    -0.68
     betweenstory
    -0.67
     تضيفلها
    -0.66
    Filmografia
    -0.61
    httphttps
    -0.61
     manslaughter
    -0.57
    SharedDtor
    -0.57
     Lightboxes
    -0.56
     başına
    -0.56
    POSITIVE LOGITS
     Father
    1.69
    Father
    1.40
     Mother
    1.35
    Mother
    1.16
     Son
    0.92
     Sister
    0.91
     Padre
    0.89
     Père
    0.88
     Fathers
    0.87
     FATHER
    0.85
    Activations Density 0.086%

    No Known Activations