© 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 - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8298
    Prev
    Next
    INDEX
    Explanations

    tokens or phrases related to blank spaces or separators in text

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

    HTML or code snippets

    np_acts-logits-general · gemini-2.0-flash

    mathematical or code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    er
    -1.07
    rd
    -0.82
     par
    -0.78
    ler
    -0.78
    достатки
    -0.75
     Lili
    -0.74
    ner
    -0.74
    ar
    -0.73
    erle
    -0.72
    erl
    -0.72
    POSITIVE LOGITS
        
    1.22
    0.93
    RenderAtEndOf
    0.80
         
    0.77
      
    0.76
    0.76
     Britann
    0.75
     Seventeenth
    0.74
    😢
    0.74
     sacraments
    0.73
    Activations Density 0.229%

    No Known Activations