© 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. 8606
    Prev
    Next
    INDEX
    Explanations

    structured data elements related to user information and product details

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

    Code related to names and titles

    np_acts-logits-general · gemini-2.0-flash

    name and identifier

    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
     समीक्षक
    -0.67
    脚注の使い方
    -0.67
    aarrggbb
    -0.64
     <=",
    -0.60
     виправивши
    -0.58
    دانشنامهٔ
    -0.57
    DeleteBehavior
    -0.57
     ErrIntOverflow
    -0.57
    zkod
    -0.55
    
    -0.55
    POSITIVE LOGITS
     name
    0.85
     getName
    0.77
     title
    0.76
     productName
    0.76
    name
    0.75
     NAME
    0.74
     setName
    0.73
     names
    0.72
     Name
    0.72
    title
    0.71
    Activations Density 0.241%

    No Known Activations