© 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. 2-GEMMASCOPE-RES-16K
    11. 4068
    Prev
    Next
    INDEX
    Explanations

    instances of structured data definitions, particularly those with braces and semicolons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cref
    -0.50
    enciaga
    -0.44
     step
    -0.43
    ૌ
    -0.42
    thical
    -0.42
    zeh
    -0.41
    älter
    -0.41
    gyar
    -0.41
     gia
    -0.41
     semestre
    -0.40
    POSITIVE LOGITS
    InjectAttribute
    1.00
    Personendaten
    0.80
     المعيارى
    0.79
    SourceChecksum
    0.75
    UpInside
    0.74
     ویکی‌پدیا
    0.73
    UnusedPrivate
    0.72
    MigrationBuilder
    0.71
     }{@
    0.70
    addCriterion
    0.70
    Activations Density 0.169%

    No Known Activations