© 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. 1-GEMMASCOPE-RES-16K
    11. 6422
    Prev
    Next
    INDEX
    Explanations

    the word "very" indicating emphasis or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -1.04
     autant
    -0.72
     nationales
    -0.68
     τὸν
    -0.65
     maille
    -0.65
     blanches
    -0.65
     culturelles
    -0.64
     religieuses
    -0.63
     vectorielles
    -0.63
     sauvages
    -0.63
    POSITIVE LOGITS
     very
    4.19
    Very
    3.68
    very
    3.66
     Very
    3.59
    VERY
    3.07
     VERY
    3.06
     très
    2.61
     muy
    2.59
     sehr
    2.29
     очень
    2.04
    Activations Density 0.079%

    No Known Activations