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. 16446
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and operations, particularly sums and integrals

    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
    ,
    -0.56
     acon
    -0.48
     Conduct
    -0.47
    <eos>
    -0.46
    Conduct
    -0.44
    (&:
    -0.44
     ADT
    -0.43
     createdBy
    -0.43
     tricot
    -0.43
     and
    -0.43
    POSITIVE LOGITS
    fjspx
    0.64
     defaultstate
    0.60
    脚注の使い方
    0.56
    LEncoder
    0.55
    ∑
    0.54
     Vielzahl
    0.53
    usercontent
    0.52
    AnchorStyles
    0.52
    AlterField
    0.51
    initializeApp
    0.51
    Activations Density 0.052%

    No Known Activations