© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 72009
    Prev
    Next
    INDEX
    Explanations

    references to specific days or events, particularly those associated with significant occurrences like crime or important actions

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

    specific days

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     katkı
    -0.43
     andet
    -0.42
    beitung
    -0.41
    forhold
    -0.41
     continuing
    -0.41
     tikra
    -0.40
     pokrač
    -0.40
     toiminta
    -0.40
    dollis
    -0.39
    telé
    -0.39
    POSITIVE LOGITS
     day
    1.02
    day
    0.77
     día
    0.77
     DAY
    0.73
     Day
    0.73
    当天
    0.73
     giorno
    0.73
     morning
    0.71
    Day
    0.71
    DAY
    0.68
    Activations Density 0.028%

    No Known Activations