© 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. 4180
    Prev
    Next
    INDEX
    Explanations

    quantitative expressions relating to the concept of "most."

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

    "Most" followed by a preposition or adverb

    np_acts-logits-general · gemini-2.0-flash

    most of / most importantly

    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
    OGND
    -0.85
     وتسجيلات
    -0.81
     للمعارف
    -0.65
     Eud
    -0.62
     thereunder
    -0.61
    يكب
    -0.60
     دیکھیے
    -0.60
    awtextra
    -0.58
    Portale
    -0.57
     ochi
    -0.57
    POSITIVE LOGITS
     likely
    1.10
     importantly
    0.95
     of
    0.75
    likely
    0.71
    most
    0.71
     Likely
    0.71
     most
    0.69
     notably
    0.67
    MOST
    0.64
    Likely
    0.61
    Activations Density 0.092%

    No Known Activations