© 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. 9-GEMMASCOPE-RES-16K
    11. 9814
    Prev
    Next
    INDEX
    Explanations

    concepts related to trade-offs and compromises in complex systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    discussions of trade-offs between competing factors in technical or analytical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Waray
    -0.57
     auricular
    -0.48
    tagHelperRunner
    -0.48
     surla
    -0.47
     المعيارى
    -0.46
    #+#
    -0.45
     visitor
    -0.44
    ñales
    -0.44
    Cyfarwyddwr
    -0.44
    afterEach
    -0.44
    POSITIVE LOGITS
     performance
    0.61
     PERFORMANCE
    0.59
     Performance
    0.57
    Performance
    0.53
    performance
    0.52
     desempenho
    0.52
    性能
    0.51
     rendimiento
    0.50
     kinerja
    0.50
     improvement
    0.50
    Activations Density 1.106%

    No Known Activations