© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 27625
    Prev
    Next
    INDEX
    Explanations

    references to the city of Mumbai and its associated names

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Indian cities and French phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
     collection
    -0.33
    segna
    -0.33
     disegno
    -0.32
    loved
    -0.30
    like
    -0.30
     design
    -0.30
    ▒
    -0.30
    definite
    -0.30
     discorso
    -0.30
     Chal
    -0.30
    POSITIVE LOGITS
     Mumbai
    2.41
    Mumbai
    2.25
     mumbai
    1.74
     Bombay
    1.40
    umbai
    1.36
    Bombay
    1.33
     Kolkata
    1.12
     Chennai
    1.08
     Maharashtra
    1.05
    Maharashtra
    1.02
    Activations Density 0.001%

    No Known Activations