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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 25-GEMMASCOPE-RES-16K
    6. 7959
    Prev
    Next
    INDEX
    Explanations

    technical terms related to data handling and memory management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.59
    PreInfinity
    -0.59
    تقاوى
    -0.57
     gyhoeddwyd
    -0.57
    enumi
    -0.52
     Frick
    -0.50
    onAttach
    -0.48
    脚注の使い方
    -0.48
    ്ട
    -0.47
    StoreMessageInfo
    -0.47
    POSITIVE LOGITS
     CPU
    1.08
     throughput
    0.90
     cpu
    0.90
    CPU
    0.88
     latency
    0.87
     memory
    0.86
     performance
    0.86
     RAM
    0.79
     CPUs
    0.78
     bottleneck
    0.78
    Activations Density 1.159%

    No Known Activations