© 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. 21-GEMMASCOPE-RES-16K
    11. 10467
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific formatting symbols, indicating its focus on textual structure or organization

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     enfans
    -0.74
     feroit
    -0.74
     plufieurs
    -0.72
     auroit
    -0.70
     avoient
    -0.68
     tirantes
    -0.67
     pouvoit
    -0.65
     laaj
    -0.63
     ainfi
    -0.61
     satisfecho
    -0.59
    POSITIVE LOGITS
    ="@+
    0.52
    omitempty
    0.48
     Latex
    0.48
     gql
    0.48
     B
    0.44
    Joe
    0.43
     SQLAlchemy
    0.43
     Xander
    0.42
     trolling
    0.42
     L
    0.42
    Activations Density 0.962%

    No Known Activations