© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7212
    Prev
    Next
    INDEX
    Explanations

    references to "MS" as it relates to medical or technical contexts

    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
    ContextHolder
    -0.40
    Résultats
    -0.39
     собі
    -0.38
     الرياضيه
    -0.37
     profesionales
    -0.36
     useCallback
    -0.35
    preview
    -0.35
     övers
    -0.35
    sizeCache
    -0.35
    ClientSize
    -0.35
    POSITIVE LOGITS
     Dhoni
    0.55
    tanleria
    0.55
     localObject
    0.54
    nbc
    0.51
    expandindo
    0.50
    issauga
    0.48
     mắn
    0.48
    ISSIPPI
    0.47
    CELLANEOUS
    0.46
    StoreMessageInfo
    0.44
    Activations Density 0.215%

    No Known Activations