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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8346
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and travel-related experiences

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

    Word before a location or time

    np_acts-logits-general · gemini-2.0-flash

    TIME ZONE directions

    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
     global
    -0.46
     Barangay
    -0.41
     Kelurahan
    -0.40
     незавершена
    -0.38
     Multil
    -0.38
     pok
    -0.35
    ubarak
    -0.35
     supp
    -0.35
     Soviet
    -0.35
     Ragh
    -0.35
    POSITIVE LOGITS
     northern
    0.94
     northeastern
    0.93
     southern
    0.93
     Midwest
    0.92
     southeastern
    0.85
     Northern
    0.85
    Northern
    0.83
     Southern
    0.82
    southern
    0.82
    Southern
    0.81
    Activations Density 0.501%

    No Known Activations