© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28475
    Prev
    Next
    INDEX
    Explanations

    instances of contrast or contradiction, often indicated by the word "but."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    but closed, but I come from, although the path narrows

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    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
    -0.64
     kolei
    -0.60
     препратки
    -0.56
     inoltre
    -0.52
    ceous
    -0.52
    StoreMessageInfo
    -0.52
    rira
    -0.52
    ItemGroup
    -0.51
    ClientSize
    -0.51
    لينكات
    -0.51
    POSITIVE LOGITS
     AFA
    0.63
     bevor
    0.57
     keinen
    0.56
    ThroughAttribute
    0.55
    Disliked
    0.54
    expandindo
    0.54
     keiner
    0.53
     sebelum
    0.53
     withdrew
    0.52
    cześ
    0.52
    Activations Density 0.144%

    No Known Activations