© 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. 14469
    Prev
    Next
    INDEX
    Explanations

    instances of the word "very" used to intensify descriptors

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

    "Very" followed by adjectives of quantity

    np_acts-logits-general · gemini-2.0-flash

    very few, little, short, low

    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
     sauvages
    -0.75
    IsContent
    -0.62
     segü
    -0.59
     cuno
    -0.59
     nationales
    -0.58
     culoare
    -0.56
     trecut
    -0.55
    jaciół
    -0.55
     proget
    -0.55
     toscana
    -0.54
    POSITIVE LOGITS
     VERY
    0.95
     very
    0.92
    VERY
    0.90
     Very
    0.90
    very
    0.88
    Very
    0.81
     <>",
    0.77
    หมือน
    0.75
    sehr
    0.73
    /*
    0.73
    Activations Density 0.109%

    No Known Activations