© 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. 4-GEMMASCOPE-RES-16K
    6. 11591
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Muriel
    -0.78
     pubblici
    -0.73
     Corral
    -0.73
    lop
    -0.69
    Gua
    -0.69
     Lovel
    -0.64
    Pras
    -0.64
     Indira
    -0.64
     pras
    -0.62
     Hutchison
    -0.62
    POSITIVE LOGITS
    awtextra
    1.06
    Datuak
    1.02
    "]);
    
    0.97
    findpost
    0.97
    ^{(\
    0.95
    RTN
    0.94
     мәкал
    0.94
    {{$
    0.94
    "],
    
    0.93
     MenuItem
    0.92
    Activations Density 11.332%

    No Known Activations