Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8380
    Prev
    Next
    INDEX
    Explanations

    references to platforms and their roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     suon
    -0.67
    jería
    -0.66
    entle
    -0.64
     RouterModule
    -0.64
    inheritdoc
    -0.64
     conservé
    -0.62
     hâte
    -0.62
    حياته
    -0.62
    lucene
    -0.62
     Mante
    -0.61
    POSITIVE LOGITS
     platform
    3.27
     platforms
    3.25
     Platforms
    3.01
     Platform
    3.00
    platform
    2.97
     PLATFORM
    2.83
    Platform
    2.81
     Plattform
    2.74
    platforms
    2.71
     plataforma
    2.52
    Activations Density 0.042%

    No Known Activations