© 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 - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 7844
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to processes and functions in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    parsedMessage
    -0.85
    PerformLayout
    -0.80
     AssemblyCulture
    -0.79
     Biôgrafia
    -0.78
    CloseOperation
    -0.72
    MessageTagHelper
    -0.71
     pinulongan
    -0.69
    outWeight
    -0.68
    EndContext
    -0.66
    tanleria
    -0.66
    POSITIVE LOGITS
     these
    0.60
     solchen
    0.56
     those
    0.54
    そんな
    0.51
     such
    0.51
     tersebut
    0.50
     dessas
    0.50
     solche
    0.49
    そのような
    0.48
     solches
    0.48
    Activations Density 1.052%

    No Known Activations