© 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. 16-GEMMASCOPE-RES-16K
    6. 3692
    Prev
    Next
    INDEX
    Explanations

    descriptions of handmade or crafted items

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

    preceding "small", "costs", or numbers

    np_acts-logits-general · gemini-2.0-flash

    material costs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     erecting
    -0.48
    ArgumentParser
    -0.45
     poisoning
    -0.43
     Приступљено
    -0.43
    })()
    -0.43
     contested
    -0.43
    Geplaatst
    -0.43
     costru
    -0.42
    udessa
    -0.42
     setObject
    -0.42
    POSITIVE LOGITS
     sélectionné
    0.67
     Random
    0.66
     RANDOM
    0.64
    Qualität
    0.63
    quality
    0.62
    Random
    0.61
    irregular
    0.61
     quality
    0.61
     random
    0.61
     irregularity
    0.60
    Activations Density 0.174%

    No Known Activations