© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11276
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and certain structural elements in a list or programming context

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.86
     Administrativna
    -0.80
    Identyfik
    -0.75
     transfieras
    -0.74
     nahilalakip
    -0.67
     ComVisible
    -0.66
     ModelExpression
    -0.66
    SPATH
    -0.65
    出版年
    -0.64
     ✭✭
    -0.63
    POSITIVE LOGITS
     comparación
    0.34
     uyar
    0.33
     testigos
    0.31
     lukisan
    0.31
     expansión
    0.31
     koń
    0.31
     pedig
    0.31
     terakhir
    0.30
    projectId
    0.30
     šo
    0.30
    Activations Density 0.627%

    No Known Activations