© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13469
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the importance of essential elements or qualities related to life, society, and ethics

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

    "is" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    statements of being or quality

    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
    dataloader
    -0.47
    errHandler
    -0.46
    because
    -0.46
     ones
    -0.45
     Because
    -0.43
     because
    -0.43
     weil
    -0.43
    ämmer
    -0.42
    hasil
    -0.42
    క్ష
    -0.42
    POSITIVE LOGITS
    AndEndTag
    0.91
    تقاوى
    0.90
     AssemblyCulture
    0.88
    ImageContext
    0.81
    AsUp
    0.79
     ProtoMessage
    0.79
     everywhere
    0.78
    AnimationsModule
    0.77
    EndGlobalSection
    0.77
     overrated
    0.74
    Activations Density 0.403%

    No Known Activations