© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14392
    Prev
    Next
    INDEX
    Explanations

    terms related to hierarchical structures, specifically those that indicate a master-slave relationship

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

    "master" and its related usages

    np_acts-logits-general · gemini-2.0-flash

    master device or list

    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
    <bos>
    -0.42
    Oise
    -0.37
    devším
    -0.36
    <tr>
    -0.36
    <h3>
    -0.35
    ッズ
    -0.35
     lixo
    -0.35
     Meksika
    -0.34
    Crying
    -0.34
     atheism
    -0.34
    POSITIVE LOGITS
     MASTER
    0.97
     master
    0.95
     Master
    0.93
    Master
    0.81
    MASTER
    0.80
     mastered
    0.79
    mybatisplus
    0.79
    master
    0.78
     mastering
    0.78
     للاسماء
    0.76
    Activations Density 0.150%

    No Known Activations