© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4299
    Prev
    Next
    INDEX
    Explanations

    terms related to clinical or medical interventions, evaluations, and processes in healthcare settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -1.05
     particolar
    -1.02
     equipments
    -1.00
    ContentAsync
    -0.99
     exportation
    -0.99
     للمعارف
    -0.99
     sûrement
    -0.98
     Nowadays
    -0.97
    TypedDataSet
    -0.96
     GenerationType
    -0.96
    POSITIVE LOGITS
    FWIW
    0.75
     weitgehend
    0.65
     freilich
    0.64
     broadly
    0.63
     disparate
    0.62
     increasingly
    0.60
     impri
    0.59
     compelling
    0.58
     bislang
    0.57
     fides
    0.57
    Activations Density 9.170%

    No Known Activations