© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 9631
    Prev
    Next
    INDEX
    Explanations

    phrases and keywords related to data handling and database operations

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

    Fetches data or queries

    np_acts-logits-general · gemini-2.0-flash

    fetching data from database

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fillType
    -0.56
    windowFixed
    -0.53
    Geplaatst
    -0.49
     completas
    -0.49
    EndGlobalSection
    -0.48
    ineno
    -0.47
     kív
    -0.47
     <=",
    -0.47
    vrons
    -0.46
    CGRectMake
    -0.45
    POSITIVE LOGITS
     database
    1.05
     databases
    0.96
    database
    0.89
     repository
    0.84
    migrationBuilder
    0.82
     Database
    0.78
     repositories
    0.77
    Database
    0.77
    数据库
    0.76
     DB
    0.71
    Activations Density 0.434%

    No Known Activations