© 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. 14-GEMMASCOPE-RES-16K
    11. 10298
    Prev
    Next
    INDEX
    Explanations

    references to time-related words, particularly focusing on "this" and "last."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AlterField
    -0.62
    ={<
    -0.56
     Walkover
    -0.56
    mede
    -0.54
    AddField
    -0.53
    migrationBuilder
    -0.53
    asının
    -0.53
    timbangkan
    -0.53
    Binds
    -0.52
    requestCode
    -0.51
    POSITIVE LOGITS
     week
    0.82
     year
    0.77
     Sunday
    0.73
     morning
    0.71
     Saturday
    0.70
     lenker
    0.69
     Thursday
    0.67
     day
    0.66
    tvguidetime
    0.66
     month
    0.65
    Activations Density 0.157%

    No Known Activations