© 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. 37-GEMMASCOPE-RES-16K
    11. 7875
    Prev
    Next
    INDEX
    Explanations

    references to the number of animals, specifically cats and kittens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Quiénes
    -0.34
     nakalista
    -0.33
    Tikang
    -0.31
    wärts
    -0.31
     kurtka
    -0.29
     sobremesa
    -0.29
     mengan
    -0.28
     pinggang
    -0.28
     účast
    -0.28
     Glaubens
    -0.27
    POSITIVE LOGITS
     breeding
    1.31
     breeders
    1.29
     breeder
    1.29
     cages
    1.17
    breeding
    1.14
     Breeding
    1.13
     bred
    1.12
     cage
    1.11
     petting
    1.09
     breeds
    1.08
    Activations Density 0.367%

    No Known Activations