© 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. 37-GEMMASCOPE-RES-16K
    11. 4021
    Prev
    Next
    INDEX
    Explanations

    scientific terms and references related to medical procedures and studies

    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
     Bourgoin
    -0.43
     comuniques
    -0.42
    ño
    -0.40
    Microkernel
    -0.40
    yntaxException
    -0.37
    node
    -0.37
    Node
    -0.36
     newOwner
    -0.36
    ÑO
    -0.35
    nodes
    -0.34
    POSITIVE LOGITS
     Na
    1.76
     na
    1.70
     NA
    1.67
     NAP
    1.60
    Na
    1.59
     Nap
    1.56
     Nav
    1.52
     NAV
    1.52
     NAC
    1.49
     nav
    1.48
    Activations Density 0.700%

    No Known Activations