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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 1240
    Prev
    Next
    INDEX
    Explanations

    references to time and current states or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     AssemblyProduct
    -0.62
    flink
    -0.62
     بيها
    -0.60
    otry
    -0.60
     initComponents
    -0.58
     ursprünglich
    -0.57
     tuttavia
    -0.57
     للمعارف
    -0.56
     connexes
    -0.56
     linkovi
    -0.56
    POSITIVE LOGITS
     now
    1.13
    Теперь
    1.02
     Теперь
    0.99
     Now
    0.92
    Now
    0.92
    now
    0.90
     NOW
    0.89
     теперь
    0.87
     ahora
    0.85
     Ahora
    0.83
    Activations Density 0.374%

    No Known Activations