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. 122943
    Prev
    Next
    INDEX
    Explanations

    quantities and financial figures related to large sums of money

    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
    AndEndTag
    -0.53
     CreateTagHelper
    -0.50
    Hentet
    -0.48
    SceneManagement
    -0.47
    findpost
    -0.44
     CascadeType
    -0.44
    -------------</
    -0.43
    
    -0.43
     noDo
    -0.43
     vPvB
    -0.43
    POSITIVE LOGITS
    thousands
    0.70
    Thousands
    0.70
     thousands
    0.70
     Thousands
    0.69
    Hundreds
    0.69
     hundreds
    0.68
     Millions
    0.68
     millions
    0.68
     Hundreds
    0.68
    数百
    0.66
    Activations Density 0.047%

    No Known Activations