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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 8201
    Prev
    Next
    INDEX
    Explanations

    terms related to plant growth and physiology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     Fish
    -0.30
     
    -0.29
     рыб
    -0.29
    lock
    -0.28
    friend
    -0.27
    &
    -0.27
    빙
    -0.27
     M
    -0.27
    sb
    -0.27
    amp
    -0.26
    POSITIVE LOGITS
    出版年
    0.78
    EDEFAULT
    0.74
     imagui
    0.72
    <unused14>
    0.71
    <unused16>
    0.71
    <unused8>
    0.71
    <unused43>
    0.71
    <unused79>
    0.71
    <unused41>
    0.71
    <pad>
    0.70
    Activations Density 0.077%

    No Known Activations