© 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. 7-GEMMASCOPE-RES-16K
    11. 4820
    Prev
    Next
    INDEX
    Explanations

    functions and methods related to parsing and syntax analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     &___
    -1.09
     numberWith
    -0.99
    ьаж
    -0.95
    Obrázky
    -0.92
    WebVitals
    -0.91
     ControllerBase
    -0.91
     @"/
    -0.91
    serviceWorker
    -0.90
     noDo
    -0.90
    runApp
    -0.89
    POSITIVE LOGITS
    Parser
    1.59
     parser
    1.57
     parse
    1.56
     Parse
    1.47
     Parser
    1.46
     parsing
    1.45
    parse
    1.43
    Parse
    1.36
    parser
    1.34
     Parsing
    1.33
    Activations Density 0.065%

    No Known Activations