© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1750
    Prev
    Next
    INDEX
    Explanations

    financial figures, particularly large sums of money and economic data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :+:
    -0.40
     ApiClient
    -0.38
    queryInterface
    -0.38
     WORKSHOP
    -0.38
    /*---
    -0.38
    AutoSize
    -0.37
     peu
    -0.36
     sensi
    -0.35
     flex
    -0.34
     automat
    -0.34
    POSITIVE LOGITS
     billion
    1.23
     trillion
    1.12
     Milliarden
    1.08
    billion
    1.08
     billions
    1.06
     milliards
    1.06
     triliun
    0.99
     Billion
    0.98
     milliard
    0.94
     miliardi
    0.93
    Activations Density 0.231%

    No Known Activations