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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8992
    Prev
    Next
    INDEX
    Explanations

    references to names and titles of people, companies, and notable entities

    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
     danger
    -0.34
     representative
    -0.29
    danger
    -0.27
     Gefahr
    -0.27
    Edm
    -0.26
     reposer
    -0.25
     Haftung
    -0.25
    openzeppelin
    -0.25
    stalt
    -0.25
     useState
    -0.25
    POSITIVE LOGITS
     renamed
    1.13
     rename
    0.96
     name
    0.94
     이름
    0.90
     renaming
    0.89
    rungsseite
    0.86
     Rename
    0.85
     tên
    0.79
     names
    0.79
    名字
    0.78
    Activations Density 0.380%

    No Known Activations