© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1711
    Prev
    Next
    INDEX
    Explanations

    references to the chemical compound "des" or related derivatives

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

    Follows French article "des"

    np_acts-logits-general · gemini-2.0-flash

    des prefixes

    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
    SpringRunner
    -0.77
     McGee
    -0.68
    createServer
    -0.67
    </blockquote>
    -0.65
    teeth
    -0.65
    ızı
    -0.65
    <sub>
    -0.64
    BufferedReader
    -0.64
    ReusableCell
    -0.64
    <b>
    -0.63
    POSITIVE LOGITS
     Mero
    0.87
     Desai
    0.83
    uegos
    0.80
     ARA
    0.79
     RAC
    0.77
     Phantas
    0.74
     汉
    0.73
     Sarac
    0.73
     Vau
    0.73
     Ams
    0.72
    Activations Density 0.762%

    No Known Activations