Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 25243
    Prev
    Next
    INDEX
    Explanations

    the term "MO" indicating specific instances or references related to operational metrics or possibly geographical locations

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

    MO acronyms and abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſcher
    -0.52
     civilización
    -0.52
    iconductors
    -0.52
     Cæsar
    -0.51
    etsen
    -0.51
     يتيمه
    -0.50
    传感器
    -0.49
    acters
    -0.49
    flink
    -0.49
     manicura
    -0.49
    POSITIVE LOGITS
     MO
    2.17
    MO
    2.03
     mo
    1.02
    mo
    0.98
     MOA
    0.96
    moe
    0.93
    Mo
    0.92
     МО
    0.89
     Moe
    0.87
    Moe
    0.85
    Activations Density 0.003%

    No Known Activations