© 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. 9769
    Prev
    Next
    INDEX
    Explanations

    indications of product condition or quality issues

    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
     enfans
    -0.54
     informée
    -0.46
    +#+
    -0.44
     Grecs
    -0.42
     peuples
    -0.40
     surla
    -0.40
     féd
    -0.39
     rospy
    -0.37
    enterOuterAlt
    -0.37
     ویکی‌پدیا
    -0.37
    POSITIVE LOGITS
     blemishes
    0.98
     patches
    0.95
     spots
    0.95
     blemish
    0.89
    spots
    0.82
     stains
    0.81
     patch
    0.77
     Spots
    0.74
     scars
    0.73
     imperfections
    0.72
    Activations Density 0.419%

    No Known Activations