© 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. 3797
    Prev
    Next
    INDEX
    Explanations

    technical terminology and key concepts related to data structures and operations in programming

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

    Mathematical or chemical symbols and equations

    np_acts-logits-general · gemini-2.0-flash

    units, numbers, and codes

    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
    .*")]
    -0.71
     سكانية
    -0.56
    ponses
    -0.52
    脚注の使い方
    -0.50
    __(/*!
    -0.47
    Дереккөздер
    -0.47
    CompilerServices
    -0.46
     uParam
    -0.44
    ieteur
    -0.44
    enumii
    -0.44
    POSITIVE LOGITS
    :✨
    0.55
     EconPapers
    0.50
    ArrowToggle
    0.42
     propOrder
    0.40
     ivelany
    0.36
     genomen
    0.35
     gynhyrchwyd
    0.35
     himo
    0.34
     zwar
    0.34
    fde
    0.33
    Activations Density 1.589%

    No Known Activations