Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1443
    Prev
    Next
    INDEX
    Explanations

    dialogues or quoted speech from characters

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

    Following question from a lawyer or user

    np_acts-logits-general · gemini-2.0-flash

    addresses or titles like Mrs. and Lady

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     transfieras
    -0.59
    mybatisplus
    -0.54
     ddelwed
    -0.51
    出版年
    -0.50
    <unused87>
    -0.50
     مشين
    -0.50
    <unused49>
    -0.50
    ‌آمباردا
    -0.50
    <unused13>
    -0.50
    <unused12>
    -0.50
    POSITIVE LOGITS
    Then
    0.35
     risposta
    0.35
     sportiva
    0.33
     then
    0.32
     Then
    0.32
    例文帳に追加
    0.32
    titleMargin
    0.32
     recommandée
    0.32
    Answer
    0.31
    Answers
    0.30
    Activations Density 0.326%

    No Known Activations