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. 605
    Prev
    Next
    INDEX
    Explanations

    references to language translation and multilingualism

    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
     invokingState
    -0.43
    UrlResolution
    -0.41
    UnusedPrivate
    -0.39
    FDRE
    -0.38
    WebServlet
    -0.37
    +#+
    -0.37
    #+#
    -0.36
     OkHttpClient
    -0.35
     disambiguazione
    -0.35
     jambes
    -0.35
    POSITIVE LOGITS
     language
    0.84
     languages
    0.76
    language
    0.71
     Language
    0.70
     bilingual
    0.68
    Language
    0.66
     translated
    0.65
     Languages
    0.65
     English
    0.64
    ilingual
    0.63
    Activations Density 0.179%

    No Known Activations