© 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. 36-GEMMASCOPE-RES-16K
    11. 15950
    Prev
    Next
    INDEX
    Explanations

    references to rankings or ratings, especially in the context of apps or products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.39
     Pflanze
    -0.35
     пациентов
    -0.30
     značky
    -0.30
     породы
    -0.30
     barnen
    -0.30
     Tiere
    -0.29
     atve
    -0.29
     kommunen
    -0.29
     projektu
    -0.29
    POSITIVE LOGITS
     aviation
    0.98
     aerospace
    0.88
     automotive
    0.87
     woodworking
    0.87
     motorsport
    0.87
     skincare
    0.87
     aeronau
    0.87
     motorcycle
    0.86
     archery
    0.86
     horticultural
    0.85
    Activations Density 4.192%

    No Known Activations