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. 21-GEMMASCOPE-RES-16K
    6. 14272
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and concepts related to the Borel transform and its applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Citadel
    -0.54
    hindu
    -0.54
    onAttach
    -0.51
    RemoveField
    -0.51
     Margot
    -0.48
    Legal
    -0.47
    ظمة
    -0.45
    상
    -0.45
     phosphat
    -0.44
     Zorn
    -0.44
    POSITIVE LOGITS
     series
    0.94
    series
    0.89
     Series
    0.88
    Series
    0.86
     SERIES
    0.80
     recurrence
    0.79
    SERIES
    0.78
     sequence
    0.76
     Sequence
    0.74
     serie
    0.71
    Activations Density 2.004%

    No Known Activations