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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 3997
    Prev
    Next
    INDEX
    Explanations

    terms related to software interfaces and user experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fél
    -0.48
    innerHeight
    -0.48
    ITABLE
    -0.47
     EconPapers
    -0.47
    ุ่ม
    -0.44
     Cytometry
    -0.44
    wira
    -0.43
    imenta
    -0.43
     lateinit
    -0.42
    ناسب
    -0.42
    POSITIVE LOGITS
     propOrder
    0.82
    不过是
    0.79
     merely
    0.76
    Obrázky
    0.69
     مشين
    0.66
     Administrativna
    0.65
    只不过
    0.63
     }{@
    0.63
     Biôgrafia
    0.61
    DeleteBehavior
    0.61
    Activations Density 0.432%

    No Known Activations