© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 15284
    Prev
    Next
    INDEX
    Explanations

    components and interactions related to calcium and other biological and chemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -0.66
    URLException
    -0.61
     marié
    -0.58
     fhew
    -0.56
    RegressionTest
    -0.56
    Mojo
    -0.56
     parkir
    -0.55
     pintados
    -0.55
     useAppContext
    -0.54
    antaranya
    -0.53
    POSITIVE LOGITS
     content
    0.86
     Content
    0.67
    PreferredItem
    0.65
    TextAppearance
    0.62
    content
    0.61
    makeText
    0.60
    rijke
    0.60
     production
    0.58
     generation
    0.57
     CONTENT
    0.56
    Activations Density 1.289%

    No Known Activations