© 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-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 2498
    Prev
    Next
    INDEX
    Explanations

    programming constructs related to variable declarations and assignments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ویکی‌پدی
    -1.02
     kasarigan
    -1.00
    parsedMessage
    -0.96
     autorytatywna
    -0.91
     Roskov
    -0.89
     propOrder
    -0.88
    GEBURTSDATUM
    -0.88
    MigrationBuilder
    -0.87
     wiſſen
    -0.84
    NameInMap
    -0.81
    POSITIVE LOGITS
     both
    0.34
     either
    0.31
     is
    0.31
    SuppressMessage
    0.31
     neither
    0.31
     also
    0.30
     not
    0.30
     sometimes
    0.27
     usually
    0.26
     a
    0.25
    Activations Density 0.699%

    No Known Activations