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. 15-GEMMASCOPE-RES-16K
    6. 1498
    Prev
    Next
    INDEX
    Explanations

    sequences related to graphical user interface (GUI) and API calls

    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
     ExecuteAsync
    -1.13
    \{\\
    -0.99
     kasarigan
    -0.95
    ArgsConstructor
    -0.89
    XmlAccessType
    -0.85
    tvguidetime
    -0.85
    sizeCache
    -0.84
     autorytatywna
    -0.84
    таратура
    -0.83
    __(/*!
    -0.81
    POSITIVE LOGITS
     afterwards
    0.57
     afterward
    0.55
     danach
    0.54
     return
    0.54
     subsequent
    0.54
     End
    0.54
     end
    0.50
    End
    0.50
     thereafter
    0.50
     بعد
    0.50
    Activations Density 0.314%

    No Known Activations