© 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. 31-GEMMASCOPE-RES-16K
    11. 11527
    Prev
    Next
    INDEX
    Explanations

    mentions of medical and research institutions, as well as names of individuals related to healthcare

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words or tokens that appear in proper nouns, place names, and organizational titles.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.59
    曖昧さ回避
    -0.44
     ujednoznacz
    -0.43
     Pyongyang
    -0.41
    
    -0.38
     Ottawa
    -0.38
     Ankara
    -0.36
     Philadelphia
    -0.35
     conci
    -0.33
    积
    -0.33
    POSITIVE LOGITS
     Marathi
    1.02
     Maharashtra
    0.94
    Maharashtra
    0.85
     Nagpur
    0.68
     Pune
    0.66
     Mumbai
    0.65
    Mumbai
    0.65
     Thane
    0.60
    Pune
    0.60
     Patil
    0.60
    Activations Density 0.067%

    No Known Activations