© 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. 3-GEMMASCOPE-RES-16K
    11. 13266
    Prev
    Next
    INDEX
    Explanations

    specific scientific and medical terminology related to health and biology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     embarazada
    -0.86
     réfugiés
    -0.86
     détru
    -0.84
     isolado
    -0.83
     morire
    -0.83
     peggio
    -0.82
     sternum
    -0.82
     mitochondria
    -0.82
     rectum
    -0.82
     Ethnicity
    -0.81
    POSITIVE LOGITS
    letal
    1.28
    neurial
    1.26
    hical
    1.19
     musical
    1.11
    istic
    1.11
     behavioral
    1.10
    ressional
    1.07
    URAL
    1.07
    ULAR
    1.07
    '],
    1.07
    Activations Density 1.770%

    No Known Activations