© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 27421
    Prev
    Next
    INDEX
    Explanations

    items related to supplies and equipment

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

    lists of items or supplies

    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
    rungsseite
    -0.75
    ArrowToggle
    -0.72
    BufferException
    -0.69
     InputDecoration
    -0.66
     BoxFit
    -0.65
     مرئيه
    -0.64
    rogens
    -0.59
    Fordítás
    -0.59
    proposals
    -0.58
    XtraEditors
    -0.58
    POSITIVE LOGITS
     oprot
    0.60
     kit
    0.53
     needed
    0.53
     assortment
    0.52
     neces
    0.52
     اللا
    0.50
     kits
    0.50
     cheap
    0.49
     station
    0.48
     assorted
    0.47
    Activations Density 0.113%

    No Known Activations