© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8489
    Prev
    Next
    INDEX
    Explanations

    terms related to technology and advancements in various fields

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

    "technology" or "technological."

    np_acts-logits-general · gemini-2.0-flash

    new advanced technologies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intptr
    -0.57
    ьажоргаш
    -0.55
    فحة
    -0.54
    UTERS
    -0.54
     للاسماء
    -0.53
    TypedDataSet
    -0.53
    atschapp
    -0.52
    VITA
    -0.49
    amous
    -0.48
     kwiet
    -0.48
    POSITIVE LOGITS
     technology
    2.65
     technologies
    2.27
    technology
    2.25
     technological
    2.17
     Technology
    2.06
    Technology
    2.04
     technologie
    2.02
     tecnología
    1.98
     TECHNOLOGY
    1.95
     teknologi
    1.93
    Activations Density 0.523%

    No Known Activations