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. 9-GEMMASCOPE-RES-16K
    6. 3553
    Prev
    Next
    INDEX
    Explanations

    expressions related to dining etiquette

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TypedDataSet
    -0.93
    setVerticalGroup
    -0.76
     disambiguazione
    -0.71
     Efq
    -0.65
     EconPapers
    -0.64
     verſ
    -0.63
     ſtate
    -0.62
     lenker
    -0.62
    ViewFeatures
    -0.62
    RegistryLite
    -0.60
    POSITIVE LOGITS
     car
    0.38
    🙁
    0.30
     soaked
    0.30
     inconvénients
    0.30
     wasn
    0.30
     didn
    0.30
     interesado
    0.30
     asegur
    0.29
     interesados
    0.29
     remplacement
    0.29
    Activations Density 0.235%

    No Known Activations