© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 101482
    Prev
    Next
    INDEX
    Explanations

    phrases related to experimental challenges and limitations in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    льо
    -0.32
    더
    -0.31
    hilangan
    -0.30
     Efficiency
    -0.29
     individual
    -0.29
     separate
    -0.28
    SwingConstants
    -0.27
     figure
    -0.27
     eficiencia
    -0.27
     japones
    -0.26
    POSITIVE LOGITS
    BagConstraints
    0.62
    BagLayout
    0.60
    SequentialGroup
    0.57
    parsedMessage
    0.57
     חיצוניים
    0.55
    Portale
    0.54
     indisponible
    0.54
     समीक्षाएं
    0.53
    AccessorTable
    0.52
    UnknownFieldSet
    0.52
    Activations Density 0.169%

    No Known Activations