© 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 EvalsExportsAPI 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. 15244
    Prev
    Next
    INDEX
    Explanations

    statistical significance indicators and results related to scientific studies, particularly in health and environmental contexts

    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
     '
    -0.52
    http
    -0.52
     everyday
    -0.51
     ‘
    -0.49
     daily
    -0.49
    1
    -0.47
    inf
    -0.47
    by
    -0.47
    ↵
    -0.46
    •
    -0.45
    POSITIVE LOGITS
    sizeCache
    1.25
     ProtoMessage
    1.20
    niająca
    1.17
    MigrationBuilder
    1.10
     ModelExpression
    1.09
     Paglinawan
    1.06
    WithIOException
    1.05
     GenerationType
    1.03
    ModelSerializer
    1.02
    andExpect
    1.01
    Activations Density 2.800%

    No Known Activations