Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 12847
    Prev
    Next
    INDEX
    Explanations

    concepts related to programming and software development, particularly around class structures and inheritance in object-oriented programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     Schreib
    -0.33
     χρή
    -0.32
    admission
    -0.30
     ilan
    -0.30
     Stamm
    -0.29
     Schützen
    -0.29
     schlagen
    -0.29
     admission
    -0.29
    musi
    -0.29
     seriously
    -0.28
    POSITIVE LOGITS
     Italijanski
    0.84
    bootstrapcdn
    0.77
    oredCriteria
    0.72
     betweenstory
    0.68
    :✨
    0.67
    SpringRunner
    0.64
     onCreateView
    0.64
    出版年
    0.63
     AssemblyCompany
    0.63
     initComponents
    0.63
    Activations Density 0.090%

    No Known Activations