© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8991
    Prev
    Next
    INDEX
    Explanations

    keywords related to SQL statements and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.81
    interopRequire
    -0.79
    TestingModule
    -0.74
     MaterialApp
    -0.72
     NSCoder
    -0.69
    Aiheesta
    -0.69
    zeitig
    -0.69
    arbox
    -0.67
    RTEX
    -0.67
    مصادر
    -0.67
    POSITIVE LOGITS
    stmt
    1.71
     stmt
    1.25
    Statement
    1.06
    Stmt
    1.04
     Statement
    0.81
    STATEMENT
    0.78
     Statements
    0.71
    statement
    0.70
    Statements
    0.70
     Raman
    0.69
    Activations Density 0.148%

    No Known Activations