© 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. 10-GEMMASCOPE-RES-16K
    11. 6098
    Prev
    Next
    INDEX
    Explanations

    references to time, particularly transitions between events or seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocu
    -0.52
    esis
    -0.48
    ocats
    -0.48
    Acl
    -0.45
    骼
    -0.45
    <thead>
    -0.44
     Facult
    -0.44
    CreateMap
    -0.43
    )?.
    -0.43
    ESIS
    -0.43
    POSITIVE LOGITS
    ंदीखरीदारी
    0.92
     Roskov
    0.89
    SequentialGroup
    0.86
    NameInMap
    0.86
     propOrder
    0.81
    expandindo
    0.79
    webElementXpaths
    0.78
     betweenstory
    0.76
    IntoConstraints
    0.74
    IUrlHelper
    0.71
    Activations Density 0.215%

    No Known Activations