© 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. 21-GEMMASCOPE-RES-16K
    11. 1116
    Prev
    Next
    INDEX
    Explanations

    references to numerical values or statistical results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iloc
    -0.51
    akis
    -0.51
    Спасылкі
    -0.49
    tha
    -0.48
     thousands
    -0.46
    THA
    -0.46
    hola
    -0.46
    ghis
    -0.45
     felf
    -0.44
    gé
    -0.44
    POSITIVE LOGITS
     CreateTagHelper
    1.00
    MLLoader
    0.90
     للاسماء
    0.83
     estekak
    0.83
     kasarigan
    0.82
     ExecuteAsync
    0.80
    VersionUID
    0.78
    ValueStyle
    0.77
    Personendaten
    0.75
    Personensuche
    0.75
    Activations Density 0.200%

    No Known Activations