© 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. 14590
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and functions

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

    Code, commands, and markup

    np_acts-logits-general · gemini-2.0-flash

    code constructs like `.` or keywords

    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
    QMetaType
    -0.76
    ValueStyle
    -0.73
    reactstrap
    -0.72
    parsedMessage
    -0.72
    GEBURTS
    -0.71
     оригіналу
    -0.71
    Diweddarwch
    -0.70
    Бахар
    -0.69
    KURZBESCHREIBUNG
    -0.69
     Taktlose
    -0.68
    POSITIVE LOGITS
     v
    0.35
     pro
    0.32
    注
    0.31
    XmlAccessorType
    0.30
    core
    0.30
     под
    0.30
     gewohnt
    0.28
     δια
    0.28
     vàng
    0.28
     bı
    0.28
    Activations Density 0.670%

    No Known Activations