© 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. 13-GEMMASCOPE-RES-16K
    11. 3928
    Prev
    Next
    INDEX
    Explanations

    intensifiers and adverbs that enhance the degree of description or emotion

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     pinulongan
    -0.54
     συμβ
    -0.46
    whatever
    -0.45
    iseite
    -0.45
    Geom
    -0.42
    iNdEx
    -0.41
    CRP
    -0.40
     Niro
    -0.40
     kasarigan
    -0.40
    WAP
    -0.40
    POSITIVE LOGITS
     very
    0.73
     extremely
    0.72
     VERY
    0.70
     Very
    0.63
     foarte
    0.59
     ļoti
    0.58
     Extremely
    0.58
     väga
    0.57
    Very
    0.57
     svært
    0.56
    Activations Density 0.403%

    No Known Activations