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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1910
    Prev
    Next
    INDEX
    Explanations

    syntactical symbols and operators in a programming or mathematical context

    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
     -
    -0.49
    Figure
    -0.45
    issimi
    -0.43
     –
    -0.42
    きましたが
    -0.42
    Nov
    -0.42
    agy
    -0.42
    šn
    -0.42
    htë
    -0.42
    Fig
    -0.42
    POSITIVE LOGITS
    AddTagHelper
    0.91
    出版年
    0.83
     Réponses
    0.79
    GeneratedValue
    0.77
     EconPapers
    0.72
    MessageOf
    0.71
     estekak
    0.70
    后者
    0.70
    GraphicsUnit
    0.68
    )";
    
    0.67
    Activations Density 0.335%

    No Known Activations