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. 16-GEMMASCOPE-RES-16K
    6. 15693
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    after capitalized words/acronyms

    np_acts-logits-general · gemini-2.0-flash

    technical methods and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fjspx
    -0.96
    +#+#
    -0.95
    ParallelGroup
    -0.88
    aarrggbb
    -0.81
    клопе
    -0.78
     autorytatywna
    -0.75
    Personensuche
    -0.75
    istoitu
    -0.74
     Chwiliwch
    -0.69
    Hochspringen
    -0.68
    POSITIVE LOGITS
     című
    0.62
     section
    0.58
     series
    0.57
     facility
    0.57
     protocol
    0.57
     mechanism
    0.54
     model
    0.53
     method
    0.52
     module
    0.51
     program
    0.51
    Activations Density 0.920%

    No Known Activations