© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 6904
    Prev
    Next
    INDEX
    Explanations

    connective phrases and terms related to health and wellness

    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
     îmb
    -0.40
     something
    -0.39
    semantics
    -0.37
     rotina
    -0.35
     innamor
    -0.34
    elezo
    -0.34
     görüş
    -0.33
     îna
    -0.33
    something
    -0.33
     spreken
    -0.32
    POSITIVE LOGITS
     تضيفلها
    0.60
    الحياه
    0.59
     PeEnEo
    0.58
    ंदीखरीदारी
    0.58
     صوتيه
    0.57
    EndInit
    0.56
     للاسماء
    0.56
    ValueStyle
    0.54
    Personendaten
    0.54
    tershire
    0.53
    Activations Density 0.742%

    No Known Activations