© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 5912
    Prev
    Next
    INDEX
    Explanations

    elements of structured data or metadata in XML or HTML formats

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

    XML or HTML tags and attributes

    np_acts-logits-general · gemini-2.0-flash

    starts of technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    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
    -1.15
     utafitiHapana
    -1.07
     समीक्षक
    -1.05
    fjspx
    -1.04
    :✨
    -1.04
     Chwiliwch
    -1.04
    تقاوى
    -1.03
     ویکی‌پدی
    -1.01
    はじめに
    -1.00
    >);
    -0.99
    POSITIVE LOGITS
    备案
    0.40
    Scrolling
    0.40
    -
    0.40
     registered
    0.39
     vetro
    0.39
     so
    0.38
    成年
    0.38
     capito
    0.37
    SupportActionBar
    0.36
     viên
    0.36
    Activations Density 0.309%

    No Known Activations