© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14039
    Prev
    Next
    INDEX
    Explanations

    technical terms related to devices and their functionalities

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

    descriptions of inventions, technologies, and objects with information about when they were created or founded.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    encyclopedic, definitional prose—formal, reference-style descriptions with technical terms, specifications, titles/acronyms, and factual summaries.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    terms related to inventions, inventors, or the creation/origin of technologies/systems.

    oai_token-act-pair · deepseek-r1Triggered by @jyhe0408

    definitions or descriptions of inventions, products, or concepts, particularly in formal or encyclopedic text.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     يتيمه
    -0.88
     pinulongan
    -0.74
     kasarigan
    -0.65
     سكانية
    -0.64
    KommentareTeilen
    -0.64
    PerformLayout
    -0.63
    Дереккөздер
    -0.63
     وتسجيلات
    -0.61
     للاسماء
    -0.59
     chi̍t
    -0.58
    POSITIVE LOGITS
     surla
    0.46
     HttpNotFound
    0.39
     pungkas
    0.39
     primarily
    0.35
     chiefly
    0.34
     civilización
    0.34
    LookAnd
    0.34
    typeorm
    0.30
     atualmente
    0.29
    nikahan
    0.28
    Activations Density 0.974%

    No Known Activations