© 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. 9011
    Prev
    Next
    INDEX
    Explanations

    phrases related to injuries and medical conditions

    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
    ,
    -0.66
    Maven
    -0.59
    SceneManagement
    -0.55
    .
    -0.54
     l
    -0.49
    lež
    -0.49
    /
    -0.48
     and
    -0.47
    l
    -0.47
     ongles
    -0.47
    POSITIVE LOGITS
     myſelf
    1.00
    findpost
    0.98
    IsContent
    0.93
     disambiguazione
    0.92
     Савезне
    0.90
     raiſ
    0.87
     Efq
    0.87
     becauſe
    0.86
     Theſe
    0.86
     Jefus
    0.86
    Activations Density 0.321%

    No Known Activations