© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14445
    Prev
    Next
    INDEX
    Explanations

    operations and data types related to programming languages and data structures

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

    Data types (Bool, Double, String)

    np_acts-logits-general · gemini-2.0-flash

    data type declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    DockStyle
    -0.54
    
    -0.53
    rungsseite
    -0.51
    Referències
    -0.48
    complexContent
    -0.47
    nodoc
    -0.47
    Manbalar
    -0.47
    rawDesc
    -0.46
    javax
    -0.45
    principalColumn
    -0.45
    POSITIVE LOGITS
     pinulongan
    0.53
    ándolos
    0.51
    ándola
    0.49
     Moscú
    0.49
     autres
    0.49
     otros
    0.47
     nawr
    0.44
     autre
    0.44
    évaluateur
    0.44
     lainnya
    0.43
    Activations Density 1.081%

    No Known Activations