© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 11529
    Prev
    Next
    INDEX
    Explanations

    patterns related to computational processes involving data structures and algorithms

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

    queuing or data structures

    np_acts-logits-general · gemini-2.0-flash

    first-in-first-out or queueing mechanisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DockStyle
    -0.73
    rungsseite
    -0.65
    脚注の使い方
    -0.58
     typelib
    -0.56
    hdashline
    -0.53
     Salgado
    -0.52
    makeConstraints
    -0.52
     MainAxisSize
    -0.52
     Permalink
    -0.51
    OLEAN
    -0.51
    POSITIVE LOGITS
     queue
    0.75
    PriorityQueue
    0.73
    queue
    0.72
    Queue
    0.70
     Queue
    0.69
     FIFO
    0.69
     Priority
    0.67
    priority
    0.66
    QUEUE
    0.66
     PriorityQueue
    0.64
    Activations Density 0.363%

    No Known Activations