© 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. 4-GEMMASCOPE-RES-16K
    11. 12618
    Prev
    Next
    INDEX
    Explanations

    references to specific seasons or episodes within a series

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Montmartre
    -0.72
    swire
    -0.69
     للمعارف
    -0.68
     Obrador
    -0.68
    luigi
    -0.67
    couts
    -0.67
    %)$
    -0.66
     attent
    -0.65
    ridgeshire
    -0.65
     Abstracts
    -0.64
    POSITIVE LOGITS
     season
    2.61
     Season
    2.31
     seasons
    2.30
    Season
    2.19
    season
    2.17
     SEASON
    2.12
     Seasons
    2.01
    SEASON
    1.91
    Seasons
    1.81
    seasons
    1.75
    Activations Density 0.047%

    No Known Activations