© 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. 15-GEMMASCOPE-RES-16K
    6. 5487
    Prev
    Next
    INDEX
    Explanations

    superlative adjectives and terms of endearment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.77
    OGND
    -0.76
    Personendaten
    -0.76
    Autoritní
    -0.74
    PerformLayout
    -0.72
    بوابة
    -0.71
    expandindo
    -0.69
     lenker
    -0.68
    Geplaatst
    -0.67
    EndProject
    -0.67
    POSITIVE LOGITS
     imaginable
    0.90
     incredibly
    0.66
     absolutely
    0.62
     ever
    0.59
     incredible
    0.57
     amazing
    0.56
     coolest
    0.55
     greatest
    0.55
     wonderful
    0.54
    ویی
    0.54
    Activations Density 0.080%

    No Known Activations