© 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. 8-GEMMASCOPE-RES-16K
    11. 10858
    Prev
    Next
    INDEX
    Explanations

    structures and elements of programming language syntax, particularly those related to function and method declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -1.01
    MigrationBuilder
    -0.90
     Мексичка
    -0.89
    InSection
    -0.84
    addCriterion
    -0.83
    awaiter
    -0.80
     referrerpolicy
    -0.80
    rawDesc
    -0.79
     שוליים
    -0.79
    InjectAttribute
    -0.77
    POSITIVE LOGITS
    __":
    0.76
    ↵↵
    0.75
    __':
    0.74
    __":
    0.66
    __':
    0.66
    <eos>
    0.54
     {
    0.49
     crescente
    0.49
     folie
    0.48
    限界
    0.47
    Activations Density 0.030%

    No Known Activations