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. 14479
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to specialized fields

    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
    WriteBarrier
    -1.04
    FieldBuilder
    -0.98
     GenerationType
    -0.98
    yntaxException
    -0.95
     NSCoder
    -0.95
     Мексичка
    -0.94
    RectangleBorder
    -0.94
     myſelf
    -0.93
     Савезне
    -0.93
     ब्रेकडाउन
    -0.91
    POSITIVE LOGITS
     .
    0.64
     ,
    0.63
     ()
    0.62
     /
    0.59
    (
    0.56
     :
    0.55
    ()
    0.55
     []
    0.54
    .
    0.53
    Unknown
    0.51
    Activations Density 0.546%

    No Known Activations