© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10042
    Prev
    Next
    INDEX
    Explanations

    terms related to databases and database management systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.59
     &___
    -0.53
    contentLoaded
    -0.48
    AutoScaleMode
    -0.45
    guous
    -0.44
    setVerticalGroup
    -0.43
    CppMethod
    -0.43
    elemField
    -0.42
    artifactId
    -0.40
    RectangleBorder
    -0.40
    POSITIVE LOGITS
     db
    3.31
     DB
    3.25
    DB
    3.17
    db
    3.17
    Db
    2.77
     Db
    2.66
     database
    2.13
     Database
    2.08
    getDb
    1.92
     dbs
    1.90
    Activations Density 0.165%

    No Known Activations