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. 24-GEMMASCOPE-RES-16K
    6. 14124
    Prev
    Next
    INDEX
    Explanations

    technical terms related to sensors and their applications in technology

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

    "technology" or patented innovations

    np_acts-logits-general · gemini-2.0-flash

    technology and innovations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #
    -0.54
     intptr
    -0.52
    intah
    -0.52
    σθαι
    -0.52
    BeginContext
    -0.50
     للاسماء
    -0.47
    ьажоргаш
    -0.47
    quehanna
    -0.46
     célèbres
    -0.46
     musicales
    -0.45
    POSITIVE LOGITS
     technology
    3.13
    technology
    2.63
     technologies
    2.57
     Technology
    2.42
    Technology
    2.35
     technologie
    2.33
     TECHNOLOGY
    2.32
     tech
    2.19
     tecnología
    2.17
    TECHNOLOGY
    2.13
    Activations Density 0.579%

    No Known Activations