© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 16273
    Prev
    Next
    INDEX
    Explanations

    the brand name "Mo" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -1.11
     للاسماء
    -1.00
    الحياه
    -0.98
    SequentialGroup
    -0.97
     Taktlose
    -0.92
    Hochspringen
    -0.90
    SourceChecksum
    -0.89
    extAlignment
    -0.88
     ivelany
    -0.88
     estekak
    -0.87
    POSITIVE LOGITS
     Mo
    2.87
    Mo
    2.74
     mo
    2.54
    mo
    2.34
     MO
    1.86
    MO
    1.76
     Мо
    1.52
     мо
    1.39
    モ
    1.33
    Мо
    1.31
    Activations Density 0.113%

    No Known Activations