© 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. 18-GEMMASCOPE-RES-16K
    11. 11222
    Prev
    Next
    INDEX
    Explanations

    references to specific people and their achievements in the art world

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

    art galleries

    np_acts-logits-general · gemini-2.0-flash

    art gallery

    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
    IntoConstraints
    -0.61
    脚注の使い方
    -0.58
    SpringBootTest
    -0.54
    SpringBoot
    -0.54
    urlencoded
    -0.54
    Transcripción
    -0.53
    Stade
    -0.52
    IonicModule
    -0.47
     Seeder
    -0.47
    LoggerFactory
    -0.47
    POSITIVE LOGITS
     gallery
    1.47
     art
    1.31
     galleries
    1.25
     Gallery
    1.24
     Galleries
    1.15
    gallery
    1.12
    Gallery
    1.12
     paintings
    1.09
     galer
    1.08
     Art
    1.08
    Activations Density 0.234%

    No Known Activations