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. 12471
    Prev
    Next
    INDEX
    Explanations

    conditional statements in programming code

    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
    PerformLayout
    -0.77
    writeFieldEnd
    -0.74
    DockStyle
    -0.67
    fromnode
    -0.61
    aarrggbb
    -0.59
     iprot
    -0.54
    exitRule
    -0.54
    Хьажоргаш
    -0.51
    readFileSync
    -0.50
     BoxDecoration
    -0.49
    POSITIVE LOGITS
    fiez
    0.64
    ритори
    0.58
     />";
    0.57
     ISNI
    0.57
    ponses
    0.56
    VersionUID
    0.56
    izr
    0.54
    Diwedd
    0.53
     moeite
    0.53
     Akismet
    0.51
    Activations Density 0.061%

    No Known Activations