© 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. 6563
    Prev
    Next
    INDEX
    Explanations

    references to accompanying documents or materials

    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
     Taktlose
    -0.59
    GEBURTS
    -0.55
     Autorizaciones
    -0.53
    SharedDtor
    -0.52
     betweenstory
    -0.49
    ➟
    -0.49
     IFTT
    -0.48
     poffible
    -0.46
    ronpa
    -0.46
    hyrchwyd
    -0.45
    POSITIVE LOGITS
     accompany
    0.55
    companying
    0.54
     acompañar
    0.53
     accompanies
    0.53
    accompagnement
    0.52
     towarzys
    0.51
     accompag
    0.50
     alongside
    0.49
     obok
    0.48
     setiap
    0.48
    Activations Density 0.488%

    No Known Activations