© 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27349
    Prev
    Next
    INDEX
    Explanations

    indicators of programming code structure or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     AssemblyCulture
    -0.63
    Lähteet
    -0.45
    VersionUID
    -0.44
     Dapper
    -0.44
     Haul
    -0.43
     tehd
    -0.42
    poto
    -0.42
    Brow
    -0.40
     verrez
    -0.40
    <>();
    -0.40
    POSITIVE LOGITS
    WSGI
    1.37
    wsgi
    1.28
    asgi
    1.16
    migrationBuilder
    0.82
    !*\
    0.79
    tonode
    0.78
    CloseOperation
    0.77
    WebVitals
    0.71
    
    0.68
     ReactDOM
    0.67
    Activations Density 0.004%

    No Known Activations