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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5983
    Prev
    Next
    INDEX
    Explanations

    C and C++ data types, particularly unsigned integers and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ことなく
    -0.63
    medlem
    -0.61
    CrossRef
    -0.60
    opcao
    -0.56
    roek
    -0.56
    endpush
    -0.55
    ReadLine
    -0.54
     tissus
    -0.54
    texttt
    -0.54
    cshtml
    -0.54
    POSITIVE LOGITS
    unsigned
    2.13
     unsigned
    1.96
    Unsigned
    1.66
    UNSIGNED
    1.23
     تضيفلها
    0.94
    adecimal
    0.87
    testens
    0.86
    تقاوى
    0.85
    unmodifiable
    0.82
     ROG
    0.80
    Activations Density 0.100%

    No Known Activations