Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 10401
    Prev
    Next
    INDEX
    Explanations

    content related to the recognition and status of endangered languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     initComponents
    -0.81
    WriteAttribute
    -0.63
    ServletException
    -0.61
     مشين
    -0.60
    HttpPut
    -0.55
    CardHeader
    -0.54
    Personendaten
    -0.54
    Cyfeiriadau
    -0.53
    তথ্যসূত্র
    -0.52
    المناصب
    -0.52
    POSITIVE LOGITS
     language
    2.67
    language
    2.17
     Language
    2.13
     languages
    2.05
    Language
    2.01
     LANGUAGE
    1.94
    语言
    1.74
     langue
    1.71
     langage
    1.69
     Languages
    1.67
    Activations Density 0.314%

    No Known Activations