© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 1520
    Prev
    Next
    INDEX
    Explanations

    references to locations and administrative divisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.70
    rhein
    -0.56
     pro
    -0.55
     line
    -0.55
      
    -0.55
    FieldBuilder
    -0.55
     fø
    -0.54
     digital
    -0.52
     online
    -0.52
     physical
    -0.52
    POSITIVE LOGITS
     betweenstory
    0.81
     >=",
    0.75
     jScrollPane
    0.74
     TextAppearance
    0.73
     Signalez
    0.72
    GeoNames
    0.71
    Referencies
    0.70
     StatelessWidget
    0.70
     Савезне
    0.69
     CORS
    0.69
    Activations Density 0.131%

    No Known Activations