© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 60613
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations and streets

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

    street names and districts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.79
    principalColumn
    -0.76
     estekak
    -0.71
     nahilalakip
    -0.70
    TagMode
    -0.69
    tanleria
    -0.68
    تفصیلات
    -0.68
    رشف
    -0.67
    ReusableCell
    -0.66
    httphttps
    -0.66
    POSITIVE LOGITS
     downtown
    0.69
     Downtown
    0.64
    Downtown
    0.56
    downtown
    0.53
     Street
    0.44
     lower
    0.36
     Buildings
    0.36
     buildings
    0.36
     street
    0.35
     Lower
    0.34
    Activations Density 0.038%

    No Known Activations