© 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-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 7211
    Prev
    Next
    INDEX
    Explanations

    names of medical institutions and related organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.59
    ChildScrollView
    -0.59
     ब्रेकडाउन
    -0.57
    الحياه
    -0.53
     свер
    -0.45
     lenker
    -0.45
    Попис
    -0.42
    velocityY
    -0.41
     NgModule
    -0.39
    niająca
    -0.38
    POSITIVE LOGITS
     Korea
    1.30
     Korean
    1.29
     Seoul
    1.16
     Koreans
    1.14
    Korea
    1.07
     korean
    1.05
    Korean
    1.05
     korea
    1.02
     Corée
    1.00
     coreano
    0.96
    Activations Density 0.453%

    No Known Activations