© 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. 36-GEMMASCOPE-RES-16K
    11. 14629
    Prev
    Next
    INDEX
    Explanations

    concepts related to the duality of good and evil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.61
    Tikang
    -0.60
     embarrassment
    -0.51
    oa̍t
    -0.51
     embarrass
    -0.50
    joba
    -0.50
     embarrassing
    -0.50
    出版年
    -0.48
    onauts
    -0.48
    sandalia
    -0.47
    POSITIVE LOGITS
     evil
    2.06
    evil
    1.75
     Evil
    1.69
    Evil
    1.62
     wicked
    1.34
     villain
    1.32
     malicious
    1.26
     wickedness
    1.18
     sinister
    1.16
     зло
    1.10
    Activations Density 0.658%

    No Known Activations