© 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. 432
    Prev
    Next
    INDEX
    Explanations

    import statements that include specific libraries or modules in code.

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

    code snippets and software development tools.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to GitHub repository URLs.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Links to Github repositories

    np_acts-logits-general · gemini-2.0-flash

    github links and packages

    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
     “
    -0.63
     «
    -0.59
     ‘
    -0.56
     
    -0.52
    findpost
    -0.50
     *>(
    -0.49
    ,
    -0.48
     galima
    -0.47
     发表于
    -0.47
    AdapterView
    -0.46
    POSITIVE LOGITS
     فريبيس
    0.80
    ſelves
    0.79
     виправивши
    0.76
    InjectAttribute
    0.75
     kasarigan
    0.74
    Hochspringen
    0.72
    TagHelper
    0.72
     ―――――
    0.72
    neſs
    0.71
     متعلقه
    0.69
    Activations Density 0.056%

    No Known Activations