© 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. 18-GEMMASCOPE-RES-16K
    11. 3985
    Prev
    Next
    INDEX
    Explanations

    references to programming constructs and syntax error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code syntax and parsing

    np_acts-logits-general · gemini-2.0-flash

    programming language syntax parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     restTemplate
    -0.52
    RestTemplate
    -0.49
    principalColumn
    -0.46
    IsContent
    -0.44
    cipient
    -0.43
    Solr
    -0.43
    IsInitialized
    -0.43
     estekak
    -0.43
    kug
    -0.43
    Accessors
    -0.42
    POSITIVE LOGITS
     syntax
    0.75
     Lexer
    0.73
    compiler
    0.72
     parser
    0.71
     Interpreter
    0.69
    parser
    0.69
     sinta
    0.67
     compiler
    0.66
     parse
    0.65
     Syntax
    0.65
    Activations Density 1.059%

    No Known Activations