© 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. 27-GEMMASCOPE-RES-16K
    11. 9525
    Prev
    Next
    INDEX
    Explanations

    relational and hierarchical structures in programming and data configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.62
    OCCURRED
    -0.56
    endforeach
    -0.55
    ukone
    -0.54
    mergeFrom
    -0.52
    PerformLayout
    -0.51
    KommentareTeilen
    -0.50
    SequentialGroup
    -0.50
    parsedMessage
    -0.49
    aarrggbb
    -0.49
    POSITIVE LOGITS
     parameter
    0.91
     field
    0.72
     variable
    0.69
     attribute
    0.68
     property
    0.66
     парамет
    0.60
     Parameter
    0.59
    parameter
    0.57
     param
    0.56
     atributo
    0.56
    Activations Density 0.862%

    No Known Activations