© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1624
    Prev
    Next
    INDEX
    Explanations

    elements related to code structure and error handling in a programming context

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

    Code snippets or package names

    np_acts-logits-general · gemini-2.0-flash

    network package maker

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ,
    -0.39
     rowspan
    -0.35
     literature
    -0.35
    子
    -0.35
     is
    -0.33
     Fischer
    -0.33
     Cowan
    -0.32
     cultural
    -0.32
     democracy
    -0.32
     off
    -0.32
    POSITIVE LOGITS
    richTextPanel
    1.04
    TagMode
    0.98
    fjspx
    0.94
    出版年
    0.90
    KommentareTeilen
    0.88
    ✨:
    0.87
    ArrowToggle
    0.87
    OGND
    0.86
    kháu
    0.84
     Италијани
    0.84
    Activations Density 0.283%

    No Known Activations