© 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. 22-GEMMASCOPE-RES-16K
    11. 14503
    Prev
    Next
    INDEX
    Explanations

    references to medical symptoms and conditions, particularly in relation to viral infections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    something lessening or ceasing

    np_acts-logits-general · gemini-2.0-flash

    things ending or disappearing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.87
    UnusedPrivate
    -0.79
     betweenstory
    -0.78
     ?>/
    -0.75
    ollectionView
    -0.66
     StringTokenizer
    -0.64
    Portale
    -0.63
    ."],
    -0.63
     للمعارف
    -0.63
     Révolution
    -0.62
    POSITIVE LOGITS
     disappear
    1.44
     disappeared
    1.42
     disappears
    1.32
     disappearing
    1.30
     fade
    1.28
     fading
    1.27
     vanished
    1.25
     dissip
    1.22
     vanish
    1.21
     faded
    1.20
    Activations Density 0.567%

    No Known Activations