© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12846
    Prev
    Next
    INDEX
    Explanations

    terms related to databases and their structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     modi
    -0.54
    ellow
    -0.53
    eid
    -0.52
    parsedMessage
    -0.52
    Teil
    -0.52
    Factor
    -0.52
    getAction
    -0.51
     CGFloat
    -0.51
     elseif
    -0.50
    Imit
    -0.50
    POSITIVE LOGITS
     database
    1.16
     Database
    1.08
    Database
    0.99
     DATABASE
    0.96
    数据库
    0.94
     databases
    0.93
     db
    0.92
     Databases
    0.91
     Datenbank
    0.89
    db
    0.88
    Activations Density 0.076%

    No Known Activations