© 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. 20-GEMMASCOPE-RES-16K
    11. 3388
    Prev
    Next
    INDEX
    Explanations

    specific code elements and structure within programming or markup languages

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

    HTML attributes and code snippets

    np_acts-logits-general · gemini-2.0-flash

    HTML closing tags and attributes

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    #+#
    -0.95
     otomatig
    -0.86
    +#+
    -0.80
    RTLD
    -0.76
     betweenstory
    -0.74
     propOrder
    -0.74
     препратки
    -0.69
    estacks
    -0.69
    脚注の使い方
    -0.69
    ########.
    -0.68
    POSITIVE LOGITS
    ">
    1.10
    '>
    0.88
     ">
    0.78
    }>
    0.77
    "><
    0.74
    ">
    0.74
    )?
    0.70
    "></
    0.68
    "?
    0.68
    ?
    0.67
    Activations Density 0.392%

    No Known Activations