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. 13983
    Prev
    Next
    INDEX
    Explanations

    structured programming contexts or code elements

    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
     kasarigan
    -0.90
    исленность
    -0.83
     CreateTagHelper
    -0.76
     referenties
    -0.75
     ddelweddau
    -0.73
     виправивши
    -0.73
     себе
    -0.72
    ViewFeatures
    -0.71
    aarrggbb
    -0.71
    rungsseite
    -0.69
    POSITIVE LOGITS
     eccell
    0.73
    adesivo
    0.57
    orithm
    0.56
    ForRow
    0.53
    \<^
    0.53
     numberWith
    0.52
    ſon
    0.51
    gorithm
    0.51
    dollis
    0.50
     razu
    0.49
    Activations Density 0.269%

    No Known Activations