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. 117245
    Prev
    Next
    INDEX
    Explanations

    articles and determiners related to objects or subjects in texts

    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
    parsedMessage
    -0.55
    RegressionTest
    -0.52
    noopener
    -0.51
     întâ
    -0.51
    Palmar
    -0.50
    ftagPool
    -0.50
     đáp
    -0.50
    prefixer
    -0.49
     ویکی‌پدی
    -0.48
    :+:
    -0.47
    POSITIVE LOGITS
     Utilizamos
    0.80
     use
    0.77
     Use
    0.76
     Utilisez
    0.76
     utiliser
    0.72
    Use
    0.71
     used
    0.71
     USE
    0.70
     usar
    0.69
     utilisez
    0.68
    Activations Density 0.023%

    No Known Activations