© 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. 27-GEMMASCOPE-RES-16K
    11. 6614
    Prev
    Next
    INDEX
    Explanations

    references to vehicle brands and models, particularly those from Volkswagen and related companies

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     giant
    -0.71
    Giant
    -0.69
    Massive
    -0.69
     gigantes
    -0.66
     massive
    -0.66
     gigantic
    -0.66
     Giant
    -0.65
     gigante
    -0.65
     Massive
    -0.65
     mammoth
    -0.63
    POSITIVE LOGITS
     tiny
    1.39
     small
    1.32
     diminutive
    1.30
    small
    1.20
    Small
    1.16
    tiny
    1.16
     pequenas
    1.16
     Small
    1.15
     piccole
    1.15
     pequeñas
    1.14
    Activations Density 0.985%

    No Known Activations