© 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-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 20507
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to programming, particularly in app development and data handling

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

    downloading, downloads, downloaded

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.47
     defaultstate
    -0.43
    thalt
    -0.43
    IUrlHelper
    -0.43
     Meksiku
    -0.41
    StructEnd
    -0.39
    ショート
    -0.39
    richTextPanel
    -0.37
    shortcuts
    -0.37
     exposição
    -0.37
    POSITIVE LOGITS
     download
    1.34
     downloading
    1.29
     downloads
    1.20
    download
    1.15
     downloaded
    1.05
     Download
    1.05
    Download
    1.01
    下载
    0.96
    ダウンロード
    0.95
     downloader
    0.93
    Activations Density 0.074%

    No Known Activations