© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 274
    Prev
    Next
    INDEX
    Explanations

    content that discusses customer support and assistance in a technical context

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

    technical specifications and parameters of equipment or products

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

    best product for customer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     définiti
    -0.78
    berdayakan
    -0.68
     déchir
    -0.68
    photobucket
    -0.67
     MessageBoxIcon
    -0.66
     vérit
    -0.66
     يتيمه
    -0.65
    gnar
    -0.64
     découver
    -0.64
    >",
    -0.63
    POSITIVE LOGITS
     peculiarities
    0.83
     («
    0.69
     «
    0.67
     attentively
    0.66
    №
    0.64
     dispu
    0.64
     peculiarity
    0.64
     №
    0.63
     Moreover
    0.63
    «
    0.63
    Activations Density 1.482%

    No Known Activations