© 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-2-2B
    7. Residual Stream - 16k
    9. 6-GEMMASCOPE-RES-16K
    11. 2076
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to deceit and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.68
    ="@+
    -0.68
    ContextCompat
    -0.66
     onResponse
    -0.65
    GetResponse
    -0.63
     donation
    -0.62
    ="<?=
    -0.61
    ColumnHeaders
    -0.61
     stanov
    -0.60
     donate
    -0.58
    POSITIVE LOGITS
     trick
    1.56
     tricks
    1.53
     Trick
    1.39
     Tricks
    1.28
    trick
    1.22
     tricked
    1.21
    tricks
    1.19
    Trick
    1.18
     manipulation
    1.07
     cunning
    1.04
    Activations Density 0.200%

    No Known Activations