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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 14-GEMMASCOPE-RES-16K
    6. 7650
    Prev
    Next
    INDEX
    Explanations

    function definitions and their structure 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 @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andExpect
    -0.95
    InputBorder
    -0.77
    躇
    -0.74
    migrationBuilder
    -0.74
    StoryboardSegue
    -0.72
    IsContent
    -0.72
    IBarButtonItem
    -0.69
     autorytatywna
    -0.65
    DataPropertyName
    -0.64
    Autoritní
    -0.62
    POSITIVE LOGITS
     phare
    0.52
     виправивши
    0.50
    ktı
    0.49
     alemanes
    0.49
    wachung
    0.48
     végétale
    0.48
     kunci
    0.45
    kozás
    0.44
    ↵↵↵
    0.43
     exatamente
    0.43
    Activations Density 0.101%

    No Known Activations