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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10132
    Prev
    Next
    INDEX
    Explanations

    descriptions and technical specifications of various types of dispensers and their functions

    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
     Zucker
    -0.33
     biens
    -0.32
    response
    -0.30
    Pointer
    -0.30
     sustancias
    -0.30
    アンケート
    -0.30
     non
    -0.29
     médec
    -0.29
    dist
    -0.29
     response
    -0.28
    POSITIVE LOGITS
     packs
    1.02
     EconPapers
    0.91
     packaged
    0.90
     packages
    0.87
     autorytatywna
    0.85
     الحره
    0.84
     Packs
    0.83
    bootstrapcdn
    0.82
     noDo
    0.79
     للاسماء
    0.79
    Activations Density 0.510%

    No Known Activations