© 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. 4-GEMMASCOPE-RES-16K
    6. 1169
    Prev
    Next
    INDEX
    Explanations

    instances of the word "under" in various grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RSpec
    -0.88
    脚注の使い方
    -0.75
     Pingback
    -0.74
    äumt
    -0.72
    pyplot
    -0.72
     HttpNotFound
    -0.71
    databind
    -0.71
     DevExpress
    -0.70
    SPJ
    -0.69
     Connexion
    -0.68
    POSITIVE LOGITS
     under
    2.71
    Under
    2.63
     Under
    2.60
    under
    2.52
     UNDER
    2.39
    UNDER
    2.33
     bajo
    1.77
    Bajo
    1.74
     sotto
    1.71
     unter
    1.70
    Activations Density 0.138%

    No Known Activations