© 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. 22-GEMMASCOPE-RES-16K
    11. 14907
    Prev
    Next
    INDEX
    Explanations

    the structure and organization of formal documents, especially focusing on sections like "Introduction."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     abge
    -0.41
     שוליים
    -0.41
     gezet
    -0.38
     provisional
    -0.38
    ]=>
    -0.38
     afge
    -0.37
     trekken
    -0.36
    Aiheesta
    -0.36
     noemen
    -0.36
     sichtbar
    -0.35
    POSITIVE LOGITS
    AndEndTag
    0.83
    OVERVIEW
    0.64
    Purpose
    0.63
    PURPOSE
    0.61
     Overview
    0.61
    Introduction
    0.61
     للاسماء
    0.60
     Purpose
    0.60
    INTRODUCTION
    0.60
     purpose
    0.60
    Activations Density 0.410%

    No Known Activations