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. 5-GEMMASCOPE-RES-16K
    6. 1734
    Prev
    Next
    INDEX
    Explanations

    references to words, vocabulary, and language use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Życiorys
    -0.61
    IUrlHelper
    -0.58
    {(-
    -0.56
     Partager
    -0.54
    colazione
    -0.54
     RSSSF
    -0.53
     ['./
    -0.52
     poffe
    -0.52
     Lalu
    -0.51
    "]];
    -0.50
    POSITIVE LOGITS
     words
    2.15
     Words
    1.93
     word
    1.83
    Words
    1.82
     WORDS
    1.78
    words
    1.67
     palabra
    1.52
     palabras
    1.51
    word
    1.47
     Word
    1.45
    Activations Density 0.236%

    No Known Activations