© 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. 4-GEMMASCOPE-RES-16K
    11. 1253
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time duration or continuity

    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
     oprot
    -0.60
    *)((
    -0.56
    حياته
    -0.55
    jetunion
    -0.51
    envolvimento
    -0.50
     Comer
    -0.50
    TagMode
    -0.49
    >>()
    -0.48
    ichthys
    -0.47
     tuong
    -0.47
    POSITIVE LOGITS
     until
    1.70
     till
    1.55
    until
    1.54
    Until
    1.48
     untill
    1.46
     Until
    1.46
     UNTIL
    1.45
    Till
    1.36
     hasta
    1.33
     TILL
    1.29
    Activations Density 0.202%

    No Known Activations