© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9107
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "mer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boulogne
    -0.66
    Примечания
    -0.64
    IMPORTED
    -0.63
     README
    -0.61
     Josephus
    -0.61
     Pingback
    -0.60
     Hentet
    -0.59
    atimes
    -0.59
     montagna
    -0.59
     للاسماء
    -0.58
    POSITIVE LOGITS
    mers
    0.80
     liter
    0.73
     algo
    0.70
    mer
    0.69
     leap
    0.68
     liters
    0.66
    liter
    0.64
    MER
    0.63
    Struct
    0.62
    ners
    0.62
    Activations Density 0.075%

    No Known Activations