© 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. 24-GEMMASCOPE-RES-16K
    6. 12098
    Prev
    Next
    INDEX
    Explanations

    references to countries with notable travel attractions or qualities

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

    cities, countries, or cultures

    np_acts-logits-general · gemini-2.0-flash

    population, culture, and infrastructure

    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
    addGap
    -0.61
     MotionEvent
    -0.60
     跳转至
    -0.60
    Handlung
    -0.57
     PropertyChanged
    -0.56
    EDEFAULT
    -0.55
    GOTREF
    -0.54
     MonoBehaviour
    -0.54
    ContentValues
    -0.53
     ISNI
    -0.53
    POSITIVE LOGITS
     population
    1.10
    Population
    0.86
     GDP
    0.85
    population
    0.84
     Population
    0.83
     culture
    0.81
     cuisine
    0.81
     infrastructure
    0.79
     tourism
    0.79
     inhabitants
    0.77
    Activations Density 0.315%

    No Known Activations