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. 1-GEMMASCOPE-RES-16K
    6. 6018
    Prev
    Next
    INDEX
    Explanations

    the concept of "wholeness" or "completeness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.83
     Majefty
    -0.77
     Jefus
    -0.71
     depositphotos
    -0.71
    neſs
    -0.70
     Macedonian
    -0.69
     Latvian
    -0.69
    seamnă
    -0.69
     Pingback
    -0.68
     Anſ
    -0.67
    POSITIVE LOGITS
     entire
    0.68
     the
    0.64
    Portale
    0.62
     overall
    0.61
     whole
    0.57
     keseluruhan
    0.56
    retum
    0.56
    IVEREF
    0.55
     весь
    0.55
    RegistryLite
    0.54
    Activations Density 0.107%

    No Known Activations