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. 57296
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to key factors, criteria, and conditions in a variety of contexts

    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
    TagHelper
    -0.54
     linkovi
    -0.40
    Regardless
    -0.38
    TagMode
    -0.36
     Regardless
    -0.36
     useHistory
    -0.35
     sortie
    -0.35
     بص
    -0.34
     CreateTagHelper
    -0.33
    Vorlage
    -0.33
    POSITIVE LOGITS
     للاسماء
    0.62
     easier
    0.54
     easy
    0.52
    Easy
    0.50
    easy
    0.49
     آسان
    0.49
    易
    0.49
     ब्रेकडाउन
    0.48
    Easier
    0.47
     Easy
    0.45
    Activations Density 0.134%

    No Known Activations