© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 13786
    Prev
    Next
    INDEX
    Explanations

    references to software, programming languages, and data-related terms

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

    Abbreviations, initialisms, and acronyms

    np_acts-logits-general · gemini-2.0-flash

    UBL, UL, UY, U, UInt, u, UI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zau
    -0.35
    sweise
    -0.34
    Amicalement
    -0.34
    Cómo
    -0.32
    pit
    -0.31
    Puedo
    -0.31
    ════
    -0.30
    Quién
    -0.29
    übers
    -0.29
     Sahne
    -0.29
    POSITIVE LOGITS
    GEBURTSDATUM
    0.75
     pinulongan
    0.75
    
    0.73
    yntaxException
    0.67
     U
    0.66
    VersionUID
    0.62
     uLocal
    0.62
    mybatisplus
    0.60
    قایناق‌لار
    0.60
     Ui
    0.58
    Activations Density 0.552%

    No Known Activations