© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14987
    Prev
    Next
    INDEX
    Explanations

    SQL query constructs and commands

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

    SQL queries starting with "SELECT"

    np_acts-logits-general · gemini-2.0-flash

    SQL SELECT statements

    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
     $_"
    -0.85
    InjectAttribute
    -0.79
     photolibrary
    -0.79
     disambiguazione
    -0.79
    וויק
    -0.75
    CppMethod
    -0.75
     Theſe
    -0.73
     Forumite
    -0.71
    VIAF
    -0.70
     Jefus
    -0.70
    POSITIVE LOGITS
     distinct
    0.85
     DISTINCT
    0.84
    distinct
    0.84
    DIST
    0.76
     COUNT
    0.68
    Distinct
    0.66
     Distinct
    0.65
     *
    0.64
     *,
    0.63
    COUNT
    0.63
    Activations Density 0.107%

    No Known Activations