© 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. 20-GEMMASCOPE-RES-131K
    11. 55650
    Prev
    Next
    INDEX
    Explanations

    instances of dates, particularly those in December

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

    December dates

    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
    🏾
    -0.46
     féminine
    -0.44
    s
    -0.43
    ufficio
    -0.42
    hidup
    -0.42
    utuhkan
    -0.40
     nabíz
    -0.40
     quisiera
    -0.40
     riscos
    -0.40
     feminina
    -0.40
    POSITIVE LOGITS
     December
    1.28
    December
    1.16
     DECEMBER
    1.11
     december
    1.10
    cember
    1.03
    december
    1.01
    DECEMBER
    1.00
     Dezember
    0.97
     décembre
    0.91
     Desember
    0.90
    Activations Density 0.013%

    No Known Activations