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

    Neuronpedia

    Jacobian LensNEW
    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. 28-GEMMASCOPE-RES-16K
    11. 7606
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political figures and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Pakistan

    np_acts-logits-general · gemini-2.0-flash

    Pakistani politician

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     لئے
    -0.36
    MethodManager
    -0.32
    upassen
    -0.31
     Bow
    -0.29
    MathML
    -0.29
     indios
    -0.28
     eventdata
    -0.28
     Typically
    -0.28
    disfraz
    -0.27
     copas
    -0.27
    POSITIVE LOGITS
    Pakistan
    0.85
     Pakistan
    0.84
     Pakistani
    0.81
     Lahore
    0.76
     Islamabad
    0.75
     Sindh
    0.70
     Karachi
    0.68
     pakistan
    0.66
     Peshawar
    0.66
     Urdu
    0.61
    Activations Density 0.046%

    No Known Activations