© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 5834
    Prev
    Next
    INDEX
    Explanations

    syntax and structure elements in code, particularly those related to metadata or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NameInMap
    -0.99
     سكانية
    -0.96
    kloped
    -0.94
    UrlResolution
    -0.88
     فريبيس
    -0.87
    MemoryWarning
    -0.85
    queryInterface
    -0.82
     protoimpl
    -0.81
     دیکھیے
    -0.80
    Personendaten
    -0.77
    POSITIVE LOGITS
    The
    0.55
     _("
    0.51
     $("<
    0.48
    dev
    0.43
     "{\"
    0.43
    Y
    0.42
    (__('
    0.42
    ది
    0.42
    слу
    0.41
    Z
    0.41
    Activations Density 0.046%

    No Known Activations