© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 11369
    Prev
    Next
    INDEX
    Explanations

    topics related to children's development and parenting strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     couvert
    -0.32
     sartén
    -0.32
     Romano
    -0.31
    anud
    -0.31
     cubierto
    -0.31
     Unterscheidung
    -0.30
     quitté
    -0.30
     Trennung
    -0.29
    ้งาน
    -0.29
     proposed
    -0.29
    POSITIVE LOGITS
     dabei
    1.41
     daarbij
    1.16
    Dabei
    1.08
     Dabei
    1.05
     thereby
    0.85
     meanwhile
    0.82
     thereupon
    0.79
     melakukannya
    0.78
     hierbei
    0.77
     بذلك
    0.77
    Activations Density 0.397%

    No Known Activations