© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 12731
    Prev
    Next
    INDEX
    Explanations

    content related to ongoing projects or developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words and phrases indicating ongoing or continuous temporal progression, particularly "to," "continues," "continuing," and time-related expressions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     eventually
    -0.86
    eventually
    -0.82
     Eventually
    -0.80
     later
    -0.79
     then
    -0.79
    Eventually
    -0.77
     initially
    -0.75
     pozdě
    -0.74
    later
    -0.73
     Later
    -0.73
    POSITIVE LOGITS
     now
    0.93
     сейчас
    0.81
     today
    0.77
     actuellement
    0.77
     currently
    0.76
     derzeit
    0.73
     ngayon
    0.72
     actualmente
    0.71
     atualmente
    0.71
    now
    0.70
    Activations Density 0.489%

    No Known Activations