© 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. 7018
    Prev
    Next
    INDEX
    Explanations

    sections or indicators of code comments and documentation

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

    Code comments and headers

    np_acts-logits-general · gemini-2.0-flash

    code comments and documentation

    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
    bootstrapcdn
    -0.71
     spacy
    -0.55
    DOCTYPE
    -0.53
     ArrayAdapter
    -0.53
    gameserver
    -0.52
     typename
    -0.52
    ècie
    -0.52
    AsUp
    -0.52
    Ӧ
    -0.50
     tensorflow
    -0.50
    POSITIVE LOGITS
    Datuak
    0.76
     autorytatywna
    0.73
    RenderAtEndOf
    0.73
    Rohy
    0.65
    engelsk
    0.55
    mergeFrom
    0.51
    ArgumentParser
    0.49
    älfte
    0.49
    BeginContext
    0.48
     iArr
    0.47
    Activations Density 0.346%

    No Known Activations