© 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. 37-GEMMASCOPE-RES-16K
    11. 3608
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and scientific terms related to genetics and cancer research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spre
    -0.32
     Spre
    -0.30
    enservice
    -0.28
     argint
    -0.28
    RODUCTION
    -0.28
    endo
    -0.27
     contener
    -0.27
    向
    -0.26
     peng
    -0.26
     بع
    -0.26
    POSITIVE LOGITS
     nakalista
    0.74
    السكان
    0.67
    出版年
    0.64
    windowFixed
    0.60
    AddTagHelper
    0.58
     oprot
    0.58
    TagMode
    0.56
     Blacklist
    0.56
     Roskov
    0.54
    tagPool
    0.53
    Activations Density 0.531%

    No Known Activations