© 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. 5-GEMMASCOPE-RES-16K
    11. 10765
    Prev
    Next
    INDEX
    Explanations

    references to files and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -1.04
    NameInMap
    -1.04
    XtraReports
    -0.98
    expandindo
    -0.92
    SpringRunner
    -0.91
     reaſon
    -0.89
    tagHelperRunner
    -0.89
    ?!”
    -0.87
     Chriftian
    -0.87
     تضيفلها
    -0.86
    POSITIVE LOGITS
     file
    2.20
     files
    1.92
     File
    1.88
    file
    1.77
    File
    1.68
     FILE
    1.67
    files
    1.52
     getFile
    1.52
     Files
    1.49
    Files
    1.48
    Activations Density 0.079%

    No Known Activations