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. 6295
    Prev
    Next
    INDEX
    Explanations

    phrases related to systematic reviews and meta-analyses in scientific literature

    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
    Rüyada
    -0.76
     للمعارف
    -0.71
    ponses
    -0.70
     ſeveral
    -0.69
    uxxxx
    -0.68
    FunctionFlags
    -0.68
     Majefty
    -0.67
    >--}}
    -0.67
    Tikang
    -0.67
     pleaſure
    -0.67
    POSITIVE LOGITS
     summarize
    1.14
     summarizing
    1.08
     summar
    1.05
     summarized
    1.02
     resumen
    1.01
     summarise
    0.99
     Summar
    0.99
     summarizes
    0.96
    summar
    0.94
     summary
    0.93
    Activations Density 0.646%

    No Known Activations