© 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. 8072
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific fields or categories in a structured format, particularly those labeled as "Field" or "field."

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

    "Field" as the start of invention descriptions

    np_acts-logits-general · gemini-2.0-flash

    field of the invention

    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
     termica
    -0.67
     thermique
    -0.63
     Maddox
    -0.62
     chaude
    -0.61
     们
    -0.61
    mereka
    -0.59
     heck
    -0.59
     Knud
    -0.57
    örk
    -0.57
    wohnt
    -0.57
    POSITIVE LOGITS
     getField
    1.06
     fields
    0.88
     Fields
    0.85
     Field
    0.83
    fields
    0.82
     FIELDS
    0.81
    Fields
    0.80
     FIELD
    0.80
     field
    0.77
    FIELDS
    0.76
    Activations Density 0.222%

    No Known Activations