© 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. 2-GEMMASCOPE-RES-16K
    11. 8653
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sight" and related contexts within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jefes
    -0.52
     CanadaChoose
    -0.52
    Geplaatst
    -0.50
     présidenti
    -0.50
     ainfi
    -0.47
    TagMode
    -0.47
    
    -0.45
     cuci
    -0.44
    انتهای
    -0.44
    extré
    -0.43
    POSITIVE LOGITS
     sight
    1.07
     Sight
    1.03
    Sight
    0.90
     bodies
    0.88
    sight
    0.81
     Bodies
    0.78
    bodies
    0.69
     sights
    0.59
     voices
    0.59
    Bodies
    0.59
    Activations Density 0.071%

    No Known Activations