© 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. 10036
    Prev
    Next
    INDEX
    Explanations

    phrases and statistics related to percentages and proportions in various contexts

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

    "of" followed by "the" or a noun

    np_acts-logits-general · gemini-2.0-flash

    percentage of items

    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
     يتيمه
    -0.87
    曖昧さ回避
    -0.85
     estekak
    -0.84
     invokingState
    -0.82
    ########.
    -0.82
    DoubleQuotes
    -0.80
     linkovi
    -0.79
    Xna
    -0.78
     تضيفلها
    -0.78
    MessageTagHelper
    -0.76
    POSITIVE LOGITS
     total
    1.07
    total
    0.86
    Total
    0.80
     overall
    0.73
     totale
    0.72
     Total
    0.71
     all
    0.67
    TOTAL
    0.66
    总
    0.66
     respondents
    0.64
    Activations Density 0.277%

    No Known Activations