© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13793
    Prev
    Next
    INDEX
    Explanations

    references to locations and administrative regions

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

    Geographic locations in India

    np_acts-logits-general · gemini-2.0-flash

    Assam and Northeast India

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ica
    -0.54
    Detroit
    -0.49
     Detroit
    -0.48
     MessageBoxIcon
    -0.48
     übers
    -0.47
    Sailor
    -0.47
     Andalu
    -0.47
    modb
    -0.47
     iniziale
    -0.46
     Michigan
    -0.46
    POSITIVE LOGITS
     Assam
    0.89
     Manipur
    0.87
     Naga
    0.86
     Dima
    0.80
     Tripura
    0.74
     Guwahati
    0.73
     Northeast
    0.71
     StatefulWidget
    0.70
     HasFactory
    0.69
     Arun
    0.69
    Activations Density 0.046%

    No Known Activations