© 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. 9843
    Prev
    Next
    INDEX
    Explanations

    phrases indicating changes or transitions in context

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

    Follows transitional words/phrases

    np_acts-logits-general · gemini-2.0-flash

    transition period

    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
    ̯
    -0.83
    BufferException
    -0.63
    webElementXpaths
    -0.55
     AssemblyProduct
    -0.54
    Hentet
    -0.53
    Linki
    -0.52
    脚注
    -0.49
    Ссылки
    -0.48
    Manbalar
    -0.48
    Filmografie
    -0.47
    POSITIVE LOGITS
     meanwhile
    2.67
     meantime
    2.65
     Meanwhile
    2.38
    Meanwhile
    2.37
     frattempo
    1.96
     interim
    1.61
    Mean
    1.60
     Mean
    1.57
     Sementara
    1.48
    mean
    1.46
    Activations Density 0.234%

    No Known Activations