© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 1444
    Prev
    Next
    INDEX
    Explanations

    concepts related to population dynamics and genetic variation over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GenerationType
    -0.47
     noOf
    -0.47
    NoOf
    -0.45
     itſelf
    -0.45
     himſelf
    -0.43
     myſelf
    -0.43
    pædia
    -0.43
     Chriftian
    -0.41
     kib
    -0.41
     germs
    -0.41
    POSITIVE LOGITS
     anthropogenic
    0.78
     spatially
    0.62
     trophic
    0.62
     tasas
    0.60
     regionally
    0.59
     populations
    0.56
     annually
    0.55
     transect
    0.55
     vár
    0.55
     hábit
    0.54
    Activations Density 2.383%

    No Known Activations