© 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. 21-GEMMASCOPE-RES-16K
    11. 3096
    Prev
    Next
    INDEX
    Explanations

    discussions about policies and decisions related to healthcare and insurance coverage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     gewöhnlich
    -0.41
     recientemente
    -0.40
    enderror
    -0.40
     irmã
    -0.39
     censiti
    -0.37
     Griechen
    -0.36
     récentes
    -0.35
    recently
    -0.35
     récemment
    -0.35
    pictured
    -0.35
    POSITIVE LOGITS
     maybe
    0.62
     perhaps
    0.57
     JpaRepository
    0.54
     defaultstate
    0.53
     magari
    0.53
    TypedDataSet
    0.51
    存于互联网档案馆
    0.50
     Bep
    0.50
    也許
    0.48
     kanske
    0.48
    Activations Density 1.183%

    No Known Activations