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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15026
    Prev
    Next
    INDEX
    Explanations

    historical references and connections to sugar production

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

    Florida location mentioned with a number

    np_acts-logits-general · gemini-2.0-flash

    Florida

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.86
    MLLoader
    -0.80
     autorytatywna
    -0.78
    MessageTagHelper
    -0.76
    脚注の使い方
    -0.72
     BorderRadius
    -0.69
     Référence
    -0.69
     SEDS
    -0.66
     تضيفلها
    -0.66
     Seeder
    -0.65
    POSITIVE LOGITS
     Florida
    1.24
    Florida
    1.13
     Tampa
    1.09
     FLORIDA
    1.02
     Orlando
    0.98
     florida
    0.91
    FLOR
    0.91
    florida
    0.91
    Tampa
    0.89
    Orlando
    0.88
    Activations Density 0.274%

    No Known Activations