© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 825
    Prev
    Next
    INDEX
    Explanations

    genes and proteins related to metal transport and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.52
    ↵↵
    -0.46
     R
    -0.43
     One
    -0.43
    .
    -0.41
      
    -0.41
    ht
    -0.40
     course
    -0.39
    追
    -0.38
    ↵
    -0.38
    POSITIVE LOGITS
     propOrder
    1.29
    Hentet
    1.07
     насељу
    1.03
    Personendaten
    1.01
     myſelf
    0.97
     autorytatywna
    0.97
     незавершена
    0.95
    RegressionTest
    0.95
     تضيفلها
    0.93
    XmlAccessType
    0.92
    Activations Density 2.403%

    No Known Activations