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. 103087
    Prev
    Next
    INDEX
    Explanations

    specific punctuation marks and symbols

    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
     débil
    -0.38
     monasterio
    -0.36
     współpra
    -0.35
     extranjera
    -0.33
     alguno
    -0.33
     restauración
    -0.32
     sugerencias
    -0.31
     distinción
    -0.31
     Ergänzung
    -0.31
     pamię
    -0.31
    POSITIVE LOGITS
     queſta
    0.88
     fashiola
    0.84
    нгред
    0.84
    ſammen
    0.81
    desertcart
    0.81
     zwiſchen
    0.80
    ſelben
    0.79
    <unused43>
    0.79
     メンテナ
    0.79
    <unused17>
    0.78
    Activations Density 0.001%

    No Known Activations