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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5318
    Prev
    Next
    INDEX
    Explanations

    elements related to web design and user interface components

    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
     оригіналу
    -0.65
    ioutil
    -0.61
     <=",
    -0.53
    :+:
    -0.52
    neurial
    -0.48
    __":
    
    -0.47
    ruptedException
    -0.47
    NavController
    -0.46
     وتسجيلات
    -0.46
    MemoryWarning
    -0.45
    POSITIVE LOGITS
     tark
    0.51
    RRect
    0.49
     details
    0.41
     detalla
    0.39
     Garanti
    0.38
     described
    0.37
    seamnă
    0.37
     precision
    0.36
     cartaz
    0.35
    explique
    0.35
    Activations Density 0.549%

    No Known Activations