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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4265
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their achievements or situations

    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
    ЙТЕ
    -0.54
    stopPropagation
    -0.54
     verksamhet
    -0.52
     relevant
    -0.52
    一遍
    -0.47
    ednesday
    -0.47
     importância
    -0.46
     METHODOLOGY
    -0.46
     större
    -0.45
     referência
    -0.44
    POSITIVE LOGITS
     للاسماء
    0.88
    dailymail
    0.84
    StructEnd
    0.76
    esModule
    0.74
     للمعارف
    0.71
     Mail
    0.71
     Daily
    0.67
    Daily
    0.66
    Mail
    0.66
     Brits
    0.65
    Activations Density 0.081%

    No Known Activations