Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 70635
    Prev
    Next
    INDEX
    Explanations

    entities related to financial institutions and professional services

    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
    RegressionTest
    -0.55
    WebElementEntity
    -0.52
     EconPapers
    -0.50
    AccessorTable
    -0.50
    évaluateur
    -0.49
     متعلقه
    -0.45
     betweenstory
    -0.44
     <=",
    -0.44
     karş
    -0.42
    Diweddarwch
    -0.41
    POSITIVE LOGITS
     purpoſe
    0.66
     ſtre
    0.64
     ſtate
    0.61
     juſ
    0.61
     preſent
    0.59
     greateſt
    0.59
     global
    0.56
     worldwide
    0.56
     ſame
    0.56
     reaſon
    0.54
    Activations Density 0.050%

    No Known Activations