© 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. 3-GEMMASCOPE-RES-16K
    11. 15948
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "table" and its variations in technical or data contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SpringRunner
    -0.78
    InjectAttribute
    -0.68
     Signalez
    -0.68
    RegistryLite
    -0.65
    MLLoader
    -0.63
    ädie
    -0.61
    ItemBackground
    -0.61
     вікі
    -0.61
     CreateTagHelper
    -0.60
     ModelExpression
    -0.59
    POSITIVE LOGITS
    table
    2.51
    tables
    1.27
     table
    1.22
    TABLE
    1.21
    Table
    0.82
     TABLE
    0.81
    tableData
    0.81
    tabile
    0.76
    tability
    0.76
    tabel
    0.74
    Activations Density 0.177%

    No Known Activations