© 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. 3-GEMMASCOPE-RES-16K
    11. 10391
    Prev
    Next
    INDEX
    Explanations

    various data structure types and their operations, particularly focused on collections like lists and sets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.69
    ècie
    -0.62
    PerformLayout
    -0.57
    /*++
    -0.56
    inheritdoc
    -0.53
    曖昧さ回避
    -0.53
    ClientSize
    -0.52
    ghua
    -0.51
    LAW
    -0.51
    Pain
    -0.50
    POSITIVE LOGITS
     LinkedList
    0.87
    BlockingQueue
    0.82
     list
    0.79
    LinkedList
    0.75
     heapq
    0.75
    ollectionView
    0.73
    Deque
    0.71
    linkedList
    0.67
     насељу
    0.67
     ArrayList
    0.67
    Activations Density 0.353%

    No Known Activations