© 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. 4588
    Prev
    Next
    INDEX
    Explanations

    references to administrative and regulatory terms related to business documents and filings

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

    Mathematical or scientific notation

    np_acts-logits-general · gemini-2.0-flash

    DNA methylation or genes

    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
    脚注の使い方
    -0.63
     surla
    -0.60
    IContainer
    -0.60
    StructEnd
    -0.59
     unknownFields
    -0.58
     BoxFit
    -0.57
    ArrowToggle
    -0.56
    AnimationsModule
    -0.56
    Xna
    -0.54
    styleType
    -0.54
    POSITIVE LOGITS
    ंदीखरीदारी
    0.40
    mbggenerated
    0.34
     aprove
    0.31
     NSCoder
    0.30
     stanu
    0.30
     Ursache
    0.29
    getStringExtra
    0.29
     impossível
    0.29
     Herkunft
    0.29
     debut
    0.28
    Activations Density 2.622%

    No Known Activations