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. 21-GEMMASCOPE-RES-16K
    6. 6973
    Prev
    Next
    INDEX
    Explanations

    relationships and familial connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    脚注の使い方
    -0.90
     kaynağından
    -0.83
    DoubleQuotes
    -0.79
    EndInit
    -0.77
     "..\..\
    -0.74
    !*\
    -0.73
     مشين
    -0.72
    存于互联网档案馆
    -0.72
    :✨
    -0.68
    gdx
    -0.68
    POSITIVE LOGITS
     law
    0.94
    law
    0.94
    laws
    0.88
    -
    0.88
     laws
    0.82
    LAW
    0.76
     Law
    0.69
     Laws
    0.69
    Law
    0.68
    Laws
    0.67
    Activations Density 0.110%

    No Known Activations