© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-GEMMASCOPE-RES-16K
    11. 11208
    Prev
    Next
    INDEX
    Explanations

    the word "ve" in various contexts, indicating a focus on a specific term related to possession or relation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uesia
    -0.63
     Independiente
    -0.51
    alité
    -0.49
     minuta
    -0.49
     abenço
    -0.49
     gâ
    -0.47
    してきました
    -0.47
    Moin
    -0.46
     مواليد
    -0.46
     município
    -0.46
    POSITIVE LOGITS
     ve
    1.41
     sea
    1.00
    Sea
    1.00
     Sea
    0.95
     Ve
    0.94
    sea
    0.91
    ve
    0.85
     Seas
    0.82
    +#+#
    0.82
    useNewUrlParser
    0.81
    Activations Density 0.211%

    No Known Activations