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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9564
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal judgments and court instructions

    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
    MemoryWarning
    -0.78
    SourceChecksum
    -0.77
    الإنجليزية
    -0.73
    <?
    -0.73
     ExecuteAsync
    -0.72
    /**
    -0.71
     nahilalakip
    -0.69
     насељу
    -0.68
    bewerken
    -0.68
    Gön
    -0.67
    POSITIVE LOGITS
     regarding
    2.62
     concerning
    2.28
    regarding
    2.22
     Regarding
    2.14
     concernant
    2.11
    Regarding
    2.09
     about
    1.98
     Concerning
    1.93
     riguardo
    1.89
     mengenai
    1.81
    Activations Density 2.153%

    No Known Activations