© 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. 27-GEMMASCOPE-RES-16K
    11. 9547
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate societal critique or concerns about governance and its impact on individuals

    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
     autorytatywna
    -0.54
    Portail
    -0.53
    AddTagHelper
    -0.50
     pubb
    -0.50
    parsedMessage
    -0.50
     molto
    -0.49
     obviamente
    -0.49
    DockStyle
    -0.48
    具
    -0.47
    SourceChecksum
    -0.47
    POSITIVE LOGITS
     afhankelijk
    0.41
     considérons
    0.39
    zubauen
    0.39
    WaitGroup
    0.38
     hoeft
    0.37
    辄
    0.35
     quelcon
    0.35
     secundarios
    0.34
     exclusivas
    0.34
     stijl
    0.34
    Activations Density 0.486%

    No Known Activations