© 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. 11291
    Prev
    Next
    INDEX
    Explanations

    significant figures in architectural history

    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
    zzleHttp
    -0.53
     oef
    -0.43
    wapV
    -0.41
    udadera
    -0.40
     Geral
    -0.39
     harmless
    -0.38
     acrylique
    -0.36
    bibfield
    -0.36
    enderal
    -0.36
     femmin
    -0.36
    POSITIVE LOGITS
     designers
    0.93
     Designers
    0.88
     architects
    0.88
     design
    0.87
     architect
    0.84
     Design
    0.84
    Design
    0.82
     architectural
    0.82
     Architects
    0.82
    design
    0.81
    Activations Density 0.101%

    No Known Activations