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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5122
    Prev
    Next
    INDEX
    Explanations

    adverbs and other modifiers that express frequency or manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     ſeveral
    -0.84
    ſelves
    -0.81
     Jefus
    -0.81
     Majefty
    -0.78
     perfons
    -0.77
     Eſ
    -0.77
    ſelf
    -0.77
     Monfieur
    -0.77
     ſen
    -0.75
     Perſ
    -0.75
    POSITIVE LOGITS
    mappedBy
    0.64
     оригіналу
    0.62
    mybatisplus
    0.60
     ترین
    0.56
    стта
    0.53
    SPATH
    0.52
    ‌ترین
    0.49
    ‌تر
    0.49
     הזה
    0.49
    存于互联网档案馆
    0.49
    Activations Density 0.460%

    No Known Activations