© 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. 14797
    Prev
    Next
    INDEX
    Explanations

    terms related to artificial intelligence and its applications

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

    "AI" or "artificial intelligence"

    np_acts-logits-general · gemini-2.0-flash

    AI and artificial intelligence

    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
     martyrdom
    -0.62
     Thule
    -0.61
     réun
    -0.57
    jooq
    -0.54
    HttpPut
    -0.54
     emprunt
    -0.54
    Partager
    -0.52
    ieteur
    -0.52
     coraggio
    -0.52
     valable
    -0.51
    POSITIVE LOGITS
     AI
    1.41
     Artificial
    1.16
    AI
    1.12
     robot
    1.07
     artificial
    1.02
     automated
    0.99
    Artificial
    0.98
     ai
    0.96
     robots
    0.93
    GPT
    0.91
    Activations Density 0.338%

    No Known Activations