Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 11948
    Prev
    Next
    INDEX
    Explanations

    terms related to inventions or technological devices

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

    Inventions, construction, or fabrication

    np_acts-logits-general · gemini-2.0-flash

    invented, built, fabricated, DIY

    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
     AssemblyCulture
    -0.87
     FetchType
    -0.76
    IsMutable
    -0.74
    
    -0.74
     ExecuteAsync
    -0.71
    elemField
    -0.68
     Italijanski
    -0.67
     kasarigan
    -0.67
     noDo
    -0.66
     freshest
    -0.66
    POSITIVE LOGITS
     design
    1.11
     construction
    0.96
     designs
    0.92
     Design
    0.89
     designing
    0.85
     DIY
    0.83
    design
    0.80
     diseño
    0.80
     Designs
    0.79
     homemade
    0.78
    Activations Density 0.505%

    No Known Activations