© 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. 40-GEMMASCOPE-RES-16K
    11. 6208
    Prev
    Next
    INDEX
    Explanations

    technical terms related to medical imaging and surgical planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enggak
    -2.02
     creș
    -1.95
     ๆ
    -1.90
     și
    -1.88
     أيضاً
    -1.80
     maș
    -1.76
     Și
    -1.71
     ș
    -1.71
     ști
    -1.70
    Și
    -1.67
    POSITIVE LOGITS
     generalised
    2.16
     grossen
    2.16
     gröss
    2.14
     fertiliser
    2.11
     civilisation
    2.08
     sólo
    2.05
     organisational
    2.03
     äusser
    2.03
     organisation
    2.02
     realisation
    2.02
    Activations Density 2.788%

    No Known Activations