© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 254
    Prev
    Next
    INDEX
    Explanations

    SQL commands and their structure in code snippets

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

    SQL queries using "path" and "parentpath"

    np_acts-logits-general · gemini-2.0-flash

    Selecting data based on path and parent

    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
     estimés
    -0.76
    MigrationBuilder
    -0.71
    pragma
    -0.54
     cardiaque
    -0.54
     LocalDate
    -0.54
    queryInterface
    -0.52
    ]<<
    -0.52
    SequentialGroup
    -0.51
     deltaTime
    -0.51
    @[+][
    -0.50
    POSITIVE LOGITS
     SEO
    0.73
     seo
    0.71
    SEO
    0.63
     HTML
    0.59
     galleries
    0.58
     Fields
    0.57
     fields
    0.56
     skins
    0.55
     options
    0.55
     Joomla
    0.55
    Activations Density 0.296%

    No Known Activations