© 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. 16-GEMMASCOPE-RES-16K
    11. 4631
    Prev
    Next
    INDEX
    Explanations

    instances of coding or programming language syntax

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

    Code-related terms and function names

    np_acts-logits-general · gemini-2.0-flash

    technical context parsing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -0.69
     
    -0.67
     (
    -0.66
    ,
    -0.63
    ↵↵
    -0.61
    /
    -0.60
    -
    -0.60
    :
    -0.55
    1
    -0.55
     and
    -0.55
    POSITIVE LOGITS
    GEBURTSDATUM
    2.81
    MigrationBuilder
    2.58
    LookAnd
    2.54
    aarrggbb
    2.51
    Personendaten
    2.48
     autorytatywna
    2.48
     AssemblyCulture
    2.42
    webElementXpaths
    2.42
    InjectAttribute
    2.42
     resourceCulture
    2.31
    Activations Density 0.023%

    No Known Activations