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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6483
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to data processing and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 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
    httphttps
    -0.76
     Seeder
    -0.66
     noDo
    -0.63
     BoxFit
    -0.63
    AnimationsModule
    -0.63
    MessageTagHelper
    -0.62
    Rhestr
    -0.61
    RenderAtEndOf
    -0.60
     snippetHide
    -0.60
    RegistryLite
    -0.58
    POSITIVE LOGITS
     Zauber
    0.41
     dependencia
    0.40
     so
    0.39
     trabajado
    0.36
     adecuado
    0.35
     premise
    0.35
     reunión
    0.35
     nutrición
    0.35
     pairing
    0.35
     apropiado
    0.35
    Activations Density 1.585%

    No Known Activations