Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 4531
    Prev
    Next
    INDEX
    Explanations

    discussions related to the advantages and disadvantages of technological methods or devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.72
     propOrder
    -0.71
     okuyayım
    -0.71
    AndEndTag
    -0.68
    setupUi
    -0.67
    Erreferentziak
    -0.66
    存于互联网档案馆
    -0.65
     alphabetically
    -0.64
     apologised
    -0.60
     blest
    -0.60
    POSITIVE LOGITS
     flexibility
    0.69
     flexible
    0.69
    PyExc
    0.61
     cost
    0.59
    Advantages
    0.57
     Flexible
    0.56
    Flexibility
    0.55
    Ưu
    0.54
     Advantages
    0.54
     lack
    0.54
    Activations Density 0.864%

    No Known Activations