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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 9896
    Prev
    Next
    INDEX
    Explanations

    references to units of time, particularly minutes and seconds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.96
    NameInMap
    -0.87
    endpush
    -0.75
    Tazama
    -0.73
     NSCoder
    -0.70
    extField
    -0.70
     للاسماء
    -0.69
     connexe
    -0.69
     CiNii
    -0.67
    .•
    -0.65
    POSITIVE LOGITS
     minutes
    3.11
     Minutes
    2.71
    minutes
    2.56
    Minutes
    2.51
     MINUTES
    2.31
     minute
    2.31
    minute
    2.04
     minutos
    2.02
     Minute
    2.01
    Minute
    1.97
    Activations Density 0.043%

    No Known Activations