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. 22420
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and parameters used in equations or formulas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Special characters or tokens that mark the boundaries of code elements, often appearing in programming languages, mathematical notation, or XML/markup languages, typically surrounding parameters, variables, or syntax elements.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    /*
    -0.45
    #
    -0.42
     specimen
    -0.42
    IntoConstraints
    -0.41
     الري
    -0.41
    /**
    -0.40
     suya
    -0.39
     ​​
    -0.39
    헌
    -0.39
    Human
    -0.37
    POSITIVE LOGITS
    sizeCache
    0.75
    новниш
    0.52
     Vikipedi
    0.51
    MessageTagHelper
    0.50
    DBNull
    0.50
    ContentAsync
    0.49
    expandindo
    0.48
    principalColumn
    0.47
    IsContent
    0.46
    fjspx
    0.46
    Activations Density 0.107%

    No Known Activations