© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 1851
    Prev
    Next
    INDEX
    Explanations

    phrases related to precision and accuracy in measurements and data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.51
    SequentialGroup
    -0.49
     ProtoMessage
    -0.44
    ьаж
    -0.42
    الإنجليزية
    -0.36
     afges
    -0.33
     linkovi
    -0.33
     sostenibilidad
    -0.33
    Geplaatst
    -0.33
     oír
    -0.33
    POSITIVE LOGITS
     accuracy
    3.00
     accurate
    2.94
    accurate
    2.61
     Accuracy
    2.61
     Accurate
    2.58
     ACCUR
    2.52
    Accurate
    2.50
     precision
    2.44
    accuracy
    2.42
    Accuracy
    2.42
    Activations Density 1.078%

    No Known Activations