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. 12552
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software and operating systems

    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
    AxisAlignment
    -0.50
     endforeach
    -0.47
    MetaObject
    -0.46
     समीक्षाओं
    -0.45
     مشين
    -0.45
    KommentareTeilen
    -0.43
    ngdoc
    -0.43
    ($__
    -0.42
     насељу
    -0.42
     calldata
    -0.42
    POSITIVE LOGITS
     Windows
    1.23
    Windows
    1.06
     Microsoft
    1.02
     windows
    1.02
    windows
    0.98
     WINDOWS
    0.98
    Microsoft
    0.90
    Win
    0.86
     Win
    0.86
    WINDOWS
    0.85
    Activations Density 0.550%

    No Known Activations