© 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. 38-GEMMASCOPE-RES-16K
    11. 14901
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the status or operation of medical facilities and services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.44
     Persons
    -0.34
     Containing
    -0.33
    setImageBitmap
    -0.33
     gesucht
    -0.32
     proposte
    -0.31
     containing
    -0.31
     proposed
    -0.31
    誰が
    -0.30
    Географи
    -0.29
    POSITIVE LOGITS
     committed
    0.89
     proud
    0.80
    committed
    0.76
     headquartered
    0.71
     pleased
    0.66
     fortunate
    0.63
     expanding
    0.63
     JpaRepository
    0.62
     staffed
    0.61
     aware
    0.60
    Activations Density 0.299%

    No Known Activations