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

    Neuronpedia

    Jacobian LensNEW
    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. 2-GEMMASCOPE-RES-16K
    11. 5447
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Ko" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    翻攝
    -0.36
     Lordships
    -0.34
    %%%%%%%%%%%%%%%%
    -0.32
     Turner
    -0.31
     Zimmermann
    -0.30
    SimpleName
    -0.30
     Veld
    -0.29
    
    -0.29
    GenerationType
    -0.29
     Zimmerman
    -0.28
    POSITIVE LOGITS
     Cob
    1.52
     Coc
    1.48
     Coco
    1.48
     Coh
    1.48
    Cob
    1.44
     Cog
    1.42
     Coy
    1.41
     Ko
    1.41
    Coc
    1.40
     Covenant
    1.38
    Activations Density 0.445%

    No Known Activations