© 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. 22-GEMMASCOPE-RES-16K
    11. 16369
    Prev
    Next
    INDEX
    Explanations

    syntax-related constructs in code snippets, specifically focusing on declarations and expressions

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

    Parsing/syntax analysis and related code

    np_acts-logits-general · gemini-2.0-flash

    parser syntax analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DBNull
    -0.51
     waking
    -0.46
     ngủ
    -0.46
     beneficiary
    -0.43
     sleeping
    -0.43
    ferro
    -0.42
    ahy
    -0.42
     uova
    -0.41
     dorm
    -0.41
    acht
    -0.41
    POSITIVE LOGITS
     parser
    1.08
     parsing
    1.06
     parse
    1.03
    parser
    0.98
     Parser
    0.96
     Parsing
    0.94
    parse
    0.92
    parsing
    0.90
     grammar
    0.90
     Parse
    0.90
    Activations Density 0.827%

    No Known Activations