© 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. 16-GEMMASCOPE-RES-16K
    11. 16297
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptors indicating variations in quality or condition

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

    followed by descriptive attributes

    np_acts-logits-general · gemini-2.0-flash

    adjectives often followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crutches
    -0.82
     eigenvectors
    -0.81
     multiples
    -0.80
     sachets
    -0.78
     diagonals
    -0.77
     swabs
    -0.77
     dignité
    -0.76
     invariants
    -0.76
     bonté
    -0.76
     chandeliers
    -0.75
    POSITIVE LOGITS
     series
    0.60
     version
    0.60
    makeText
    0.59
     IBOutlet
    0.56
     vaisseaux
    0.56
     quantités
    0.52
     }}"></
    0.52
     mixture
    0.51
     intérêts
    0.51
     few
    0.50
    Activations Density 1.603%

    No Known Activations