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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12904
    Prev
    Next
    INDEX
    Explanations

    specific sequences and patterns related to programming or computational terminology, particularly in the context of resource management

    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
     виправивши
    -0.79
    modelBuilder
    -0.79
    ธ์
    -0.78
     ApiException
    -0.72
    extAlignment
    -0.71
     SafeMath
    -0.70
    MigrationBuilder
    -0.69
    SourceChecksum
    -0.69
     gratify
    -0.68
    脚注の使い方
    -0.68
    POSITIVE LOGITS
    irc
    0.60
     McDermott
    0.55
     getC
    0.54
    ch
    0.52
    yc
    0.51
    coke
    0.50
     C
    0.50
     kc
    0.49
     Waik
    0.49
    وص
    0.48
    Activations Density 0.739%

    No Known Activations