© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 3794
    Prev
    Next
    INDEX
    Explanations

    mentions of rivers and their geographical context

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

    rivers and river names

    np_acts-logits-general · gemini-2.0-flash

    names of rivers

    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
     насељу
    -0.81
    contentLoaded
    -0.79
     للمعارف
    -0.72
     referenties
    -0.65
     nakalista
    -0.64
    WebElementEntity
    -0.61
    Vidite
    -0.61
     Италијани
    -0.58
     المعيارى
    -0.57
     Italijani
    -0.56
    POSITIVE LOGITS
     river
    1.09
     River
    0.97
    river
    0.89
     rivers
    0.87
    River
    0.86
     fiume
    0.84
     RIVER
    0.83
     rivière
    0.82
     río
    0.80
     fleuve
    0.79
    Activations Density 0.132%

    No Known Activations