© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 15980
    Prev
    Next
    INDEX
    Explanations

    numerical data related to health metrics, particularly body measurements and indices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     المعيارى
    -0.49
    delwed
    -0.47
     NSCoder
    -0.43
     BorderSide
    -0.41
    WriteTagHelper
    -0.40
    Personensuche
    -0.40
     jadx
    -0.40
     Uch
    -0.38
     maximized
    -0.38
    stylers
    -0.38
    POSITIVE LOGITS
    はじめに
    0.47
     للاسماء
    0.42
    Filmografia
    0.41
    ksessa
    0.41
    ilateral
    0.40
     CURIAM
    0.40
    umably
    0.39
    Biografie
    0.39
     Downloader
    0.39
     téléchargement
    0.39
    Activations Density 2.127%

    No Known Activations