Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1516
    Prev
    Next
    INDEX
    Explanations

    syntax and structure related to database queries, specifically focusing on SQL commands and their execution

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

    Code, queries, or expressions

    np_acts-logits-general · gemini-2.0-flash

    query and statement syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •SQL-labeled features

    No Comments

    Negative Logits
    principalColumn
    -0.66
    andaag
    -0.57
    存于互联网档案馆
    -0.53
     preocu
    -0.52
    AutoField
    -0.52
    ühle
    -0.51
     invokingState
    -0.50
    portál
    -0.50
     vuitton
    -0.50
    SystemColors
    -0.49
    POSITIVE LOGITS
     expression
    1.30
     formula
    1.13
     expressions
    1.12
    expression
    1.05
     Expression
    0.97
     statement
    0.96
     sentence
    0.96
     syntax
    0.94
     formulas
    0.91
    Expression
    0.91
    Activations Density 0.865%

    No Known Activations