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. 14414
    Prev
    Next
    INDEX
    Explanations

    topics related to fashion and design trends

    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
    Autoritní
    -0.65
    WebElementEntity
    -0.46
    afficheront
    -0.46
    Bibliograf
    -0.42
     CanadaChoose
    -0.41
    はじめに
    -0.38
    CppCodeGen
    -0.38
     betweenstory
    -0.37
     [
    -0.36
    complexContent
    -0.35
    POSITIVE LOGITS
    TagMode
    0.90
     برانيه
    0.74
    tagHelperRunner
    0.69
    Життєпис
    0.63
     مشين
    0.59
    webtoken
    0.55
    IVEREF
    0.53
    XmlAccessorType
    0.53
     Superhosts
    0.50
     محفوظة
    0.49
    Activations Density 0.810%

    No Known Activations