© 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-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6839
    Prev
    Next
    INDEX
    Explanations

    temporal references or indicators of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Samstag
    -0.60
    Geplaatst
    -0.59
    Saturday
    -0.59
    rawDesc
    -0.59
    Tomorrow
    -0.59
     amanhã
    -0.59
    Dimanche
    -0.57
    脚注の使い方
    -0.57
    Tuesday
    -0.57
     saturday
    -0.57
    POSITIVE LOGITS
     late
    1.29
     early
    1.04
     fall
    0.97
     mid
    0.92
     spring
    0.90
    late
    0.79
     summer
    0.78
     autumn
    0.73
    fall
    0.69
     Fall
    0.69
    Activations Density 0.310%

    No Known Activations