© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 15141
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, particularly cities

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

    Nebraska and related locations

    np_acts-logits-general · gemini-2.0-flash

    Neb, Nebraska, Omaha, Lincoln

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Riau
    -0.52
     catalán
    -0.50
    __':
    -0.50
    MnO
    -0.49
     Clarion
    -0.46
     catalana
    -0.46
     Hernando
    -0.45
    Log
    -0.45
     الجزائر
    -0.45
    StatusOK
    -0.45
    POSITIVE LOGITS
     Nebraska
    1.49
     Omaha
    1.43
     Neb
    1.36
    Nebraska
    1.26
    Omaha
    1.21
    Neb
    1.11
     Lincoln
    1.02
    neb
    0.99
     neb
    0.99
     Hus
    0.95
    Activations Density 0.114%

    No Known Activations