© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2154
    Prev
    Next
    INDEX
    Explanations

    HTML and JavaScript elements related to change events in forms or interactive components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     userList
    -0.77
     mList
    -0.65
     pageNo
    -0.65
     newList
    -0.64
     userDao
    -0.64
     eventName
    -0.63
     umani
    -0.63
     mData
    -0.63
     currentValue
    -0.62
     isSelected
    -0.62
    POSITIVE LOGITS
     generate
    1.16
     get
    1.15
     make
    1.11
     create
    1.09
     prepare
    1.02
    generate
    1.01
     build
    0.99
     calculate
    0.99
     handle
    0.94
    create
    0.94
    Activations Density 0.423%

    No Known Activations