© 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. 3783
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to programming or software development.

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

    programming code snippets, especially related to Java and Google libraries.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    year numbers, particularly those in the 2000s and 2010s.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    Numbers or versions (e.g., "2", "2007")

    np_acts-logits-general · gemini-2.0-flash

    code punctuation and 'com'

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.97
    NameInMap
    -0.94
     Италијани
    -0.87
    Vidite
    -0.86
    WithIOException
    -0.82
    MigrationBuilder
    -0.79
    ArrowToggle
    -0.79
    yntaxException
    -0.77
     Italijanski
    -0.77
     Roskov
    -0.76
    POSITIVE LOGITS
    })();
    0.59
    ='';
    0.55
    )";
    0.54
    $.
    0.54
    :
    0.54
     .
    0.54
    }{*}{
    0.54
    fible
    0.54
    .'</
    0.54
    ".
    0.53
    Activations Density 0.378%

    No Known Activations