© 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. 3-GEMMASCOPE-RES-16K
    11. 5629
    Prev
    Next
    INDEX
    Explanations

    words related to the analysis and treatment of medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     teng
    -0.43
    Named
    -0.41
     registered
    -0.40
     pretrained
    -0.39
     licensed
    -0.38
    Declared
    -0.38
     inspired
    -0.38
    Licensed
    -0.37
     dedicated
    -0.37
     alleged
    -0.36
    POSITIVE LOGITS
     handled
    1.31
     analysed
    1.30
     analyzed
    1.29
     answered
    1.27
     examined
    1.16
     reviewed
    1.14
     treated
    1.13
     Analyzed
    1.11
     investigated
    1.11
     processed
    1.11
    Activations Density 0.325%

    No Known Activations