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. 8697
    Prev
    Next
    INDEX
    Explanations

    references to research studies and experimental procedures

    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
    KommentareTeilen
    -0.85
     MainAxisSize
    -0.82
    DockStyle
    -0.81
    RectangleBorder
    -0.80
    +#+#
    -0.74
     EconPapers
    -0.74
    UnusedPrivate
    -0.74
    rungsseite
    -0.72
    //
    -0.72
     مشين
    -0.71
    POSITIVE LOGITS
     for
    1.81
    for
    1.32
     For
    0.99
    For
    0.99
     voor
    0.97
     momentarily
    0.91
     FOR
    0.90
     briefly
    0.89
     για
    0.87
     för
    0.82
    Activations Density 0.611%

    No Known Activations