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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 14039
    Prev
    Next
    INDEX
    Explanations

    special characters or symbols related to mathematical or statistical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -1.06
     Normdatei
    -1.01
     $_"
    -1.01
     ―――――
    -0.98
    /**
    -0.96
     EconPapers
    -0.94
    AddTagHelper
    -0.94
    IsMutable
    -0.94
     GenerationType
    -0.93
    NUMX
    -0.93
    POSITIVE LOGITS
    ↵↵
    1.31
    ↵↵↵
    1.13
     The
    1.09
    ↵
    1.05
    <eos>
    1.02
    </h3>
    0.92
     It
    0.90
    .
    0.88
    ↵↵↵↵
    0.87
     In
    0.83
    Activations Density 0.724%

    No Known Activations