© 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. 2-GEMMASCOPE-RES-16K
    11. 9174
    Prev
    Next
    INDEX
    Explanations

    location-specific terms, particularly related to San Francisco and Hollywood

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RetentionPolicy
    -0.79
    ("")]
    -0.79
    ẵn
    -0.73
    kuuta
    -0.73
    TestingModule
    -0.70
    zepte
    -0.69
    出版年
    -0.69
    canestro
    -0.69
     ModelExpression
    -0.68
     Juifs
    -0.68
    POSITIVE LOGITS
     Wednesday
    0.90
    Wednesday
    0.73
     wednesday
    0.62
    м
    0.60
     Francisco
    0.60
     Cis
    0.60
    3
    0.60
     miércoles
    0.59
     Morty
    0.59
    折
    0.56
    Activations Density 0.033%

    No Known Activations