© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 28399
    Prev
    Next
    INDEX
    Explanations

    parentheses and punctuation marks in code snippets

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

    Unihemispheric sleep

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    HasAnnotation
    -0.71
    kespea
    -0.68
     astore
    -0.68
     ddelweddau
    -0.65
    celotti
    -0.64
    centralwidget
    -0.63
    roppo
    -0.62
    oczes
    -0.60
    RectangleBorder
    -0.60
     الوطنيه
    -0.60
    POSITIVE LOGITS
    Спољашње
    0.65
    djangoproject
    0.62
     linkovi
    0.59
    Zitat
    0.51
    Geplaatst
    0.51
     mostly
    0.51
     Kombat
    0.50
     souff
    0.50
     kombat
    0.49
     raccol
    0.48
    Activations Density 0.023%

    No Known Activations