© 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. 40-GEMMASCOPE-RES-16K
    11. 5986
    Prev
    Next
    INDEX
    Explanations

    political affiliations and activities of individuals in Pakistan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+
    -0.68
    
    -0.58
    GIVEREF
    -0.51
    WithIOException
    -0.51
    IVEREF
    -0.48
     ब्रेकडाउन
    -0.47
    IntoConstraints
    -0.46
     '\\;'
    -0.46
    Notae
    -0.44
    ngdoc
    -0.44
    POSITIVE LOGITS
     PPP
    0.54
     Interior
    0.53
     Bila
    0.51
     interior
    0.49
     PML
    0.49
    PPP
    0.49
     PTI
    0.47
    Interior
    0.45
    Bila
    0.43
     containers
    0.43
    Activations Density 0.252%

    No Known Activations