© 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. 21-GEMMASCOPE-RES-16K
    11. 2890
    Prev
    Next
    INDEX
    Explanations

    elements related to Android UI layout attributes and configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RTGC
    -0.93
     propOrder
    -0.70
    oa̍t
    -0.69
     ब्रेकडाउन
    -0.69
    WithIOException
    -0.68
    IsMutable
    -0.66
    featureID
    -0.66
     ModelExpression
    -0.65
     للاسماء
    -0.65
    лтамалар
    -0.64
    POSITIVE LOGITS
     aprendizagem
    0.40
    }`).
    0.37
     suprême
    0.37
     quatrième
    0.36
     spéciaux
    0.35
     rembour
    0.33
     comisión
    0.32
     temática
    0.32
     tasarım
    0.32
     asistente
    0.31
    Activations Density 0.017%

    No Known Activations