© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 7118
    Prev
    Next
    INDEX
    Explanations

    references to specific geographical locations, particularly Malta and Libya

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

    "Malta", or preceding mathematical symbols

    np_acts-logits-general · gemini-2.0-flash

    Malta and Maltese

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.70
    Personendaten
    -0.69
     виправивши
    -0.60
    daction
    -0.56
    evos
    -0.54
     Compro
    -0.54
    RegressionTest
    -0.53
     roland
    -0.52
    انيا
    -0.52
     Legendre
    -0.51
    POSITIVE LOGITS
     Malta
    0.88
    Malta
    0.85
     Maltese
    0.83
    ċ
    0.72
    ħ
    0.65
    ġ
    0.61
     Malt
    0.59
     iż
    0.56
    Ħ
    0.56
     malta
    0.55
    Activations Density 0.014%

    No Known Activations