© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 3101
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "at" and related phrases indicating location or reference points

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

    prepositions before proper nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.82
     BorderSide
    -0.66
    +#+#
    -0.62
    SharedDtor
    -0.61
    writeFieldEnd
    -0.58
     betweenstory
    -0.58
    addGap
    -0.57
    dafx
    -0.56
     FetchType
    -0.56
    transQ
    -0.55
    POSITIVE LOGITS
     تضيفلها
    0.43
    Hentet
    0.36
    بوابة
    0.35
     חיצוניים
    0.34
     familiale
    0.34
    among
    0.33
     official
    0.32
     among
    0.31
     database
    0.31
    〉
    0.31
    Activations Density 0.004%

    No Known Activations