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. 18-GEMMASCOPE-RES-16K
    6. 10561
    Prev
    Next
    INDEX
    Explanations

    discussions about the advancements and implications of quantum computing technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulite
    -0.58
    oliber
    -0.52
     Etiquette
    -0.51
    ámicas
    -0.50
    arza
    -0.49
     Italijanski
    -0.46
     clockwise
    -0.46
     vignette
    -0.46
    organizer
    -0.46
     SUDOC
    -0.45
    POSITIVE LOGITS
     advancements
    1.32
     advances
    1.30
     technologies
    1.28
     technology
    1.28
     breakthroughs
    1.27
     technological
    1.22
     innovations
    1.12
     innovation
    1.10
     developments
    1.09
     inventors
    1.07
    Activations Density 1.039%

    No Known Activations