© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 15127
    Prev
    Next
    INDEX
    Explanations

    sequential references to time and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Months
    -0.71
     décadas
    -0.63
     Months
    -0.60
    Weeks
    -0.59
    Years
    -0.59
     miesięcy
    -0.59
     década
    -0.58
     décennies
    -0.58
     meses
    -0.57
    months
    -0.57
    POSITIVE LOGITS
     ye
    1.05
     yer
    0.87
     ya
    0.82
     yea
    0.80
     Ye
    0.75
     yeah
    0.72
     y
    0.72
    Ye
    0.71
     yes
    0.70
     YE
    0.68
    Activations Density 0.214%

    No Known Activations