© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 41-GEMMASCOPE-RES-16K
    11. 4152
    Prev
    Next
    INDEX
    Explanations

    terms related to specific classifications and attributes in scientific contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Personensuche
    -0.78
     oficialmente
    -0.65
    Personendaten
    -0.63
     perfectamente
    -0.63
     cuidadosamente
    -0.62
     soigneusement
    -0.61
     perfeitamente
    -0.60
     assolutamente
    -0.58
     officially
    -0.58
     previamente
    -0.58
    POSITIVE LOGITS
     speaking
    0.97
     parlant
    0.89
     hablando
    0.84
     falando
    0.81
     worded
    0.76
     vôtre
    0.73
     Speaking
    0.71
     parlando
    0.71
    speaking
    0.70
     priced
    0.69
    Activations Density 0.542%

    No Known Activations