© 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. 9-GEMMASCOPE-RES-16K
    11. 2117
    Prev
    Next
    INDEX
    Explanations

    commercial and retail-related terms, particularly those indicating availability and distribution locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.84
    WidgetItem
    -0.65
     createSlice
    -0.63
     EventArgs
    -0.58
     Plenum
    -0.54
    >'+
    -0.53
    ิ้น
    -0.52
     MainAxisSize
    -0.52
    uddin
    -0.51
    الط
    -0.51
    POSITIVE LOGITS
     locations
    0.69
     sites
    0.65
     geographically
    0.63
     nationwide
    0.62
     Locations
    0.59
     schools
    0.58
     establishments
    0.57
     cities
    0.55
    locations
    0.54
    equipped
    0.53
    Activations Density 0.379%

    No Known Activations