© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 38337
    Prev
    Next
    INDEX
    Explanations

    temporal references related to duration and time intervals

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

    time units in scientific studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     semanas
    -0.37
     five
    -0.36
     week
    -0.35
     years
    -0.33
     weeks
    -0.33
     forever
    -0.33
    AZIONI
    -0.33
     eight
    -0.33
     six
    -0.32
     decade
    -0.32
    POSITIVE LOGITS
     AssemblyCulture
    0.75
    ValueStyle
    0.68
    AndEndTag
    0.65
    +#+#
    0.60
    ſelves
    0.60
     faſt
    0.59
    ſelf
    0.59
     otomatig
    0.55
     BoxFit
    0.54
     Anſ
    0.53
    Activations Density 0.038%

    No Known Activations