© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 8326
    Prev
    Next
    INDEX
    Explanations

    references to specific components related to pads in electronic devices, particularly in relation to their function and testing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     best
    -0.51
     care
    -0.49
     Care
    -0.47
     standard
    -0.47
     androidx
    -0.46
    iseta
    -0.46
    izan
    -0.46
     fa
    -0.44
     par
    -0.43
     har
    -0.43
    POSITIVE LOGITS
     فريبيس
    1.03
     pads
    0.97
     Pads
    0.94
    pads
    0.92
     pad
    0.85
     AssemblyProduct
    0.80
    AccessorTable
    0.80
    Hochspringen
    0.78
    StoryboardSegue
    0.78
    IsMutable
    0.77
    Activations Density 0.064%

    No Known Activations