© 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-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 6161
    Prev
    Next
    INDEX
    Explanations

    references to stuffed toys and action figures, particularly focusing on teddy bears and dolls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    بد
    -0.34
     Bowden
    -0.29
     רע
    -0.26
    awaiter
    -0.26
     état
    -0.25
     Super
    -0.25
    PhysRev
    -0.25
     High
    -0.25
     botanique
    -0.25
     Gre
    -0.25
    POSITIVE LOGITS
     toy
    1.29
     toys
    1.16
    Toy
    1.15
    toy
    1.09
     Toy
    1.05
     doll
    1.04
    toys
    1.02
     juguete
    0.98
     dolls
    0.98
     Toys
    0.95
    Activations Density 0.322%

    No Known Activations