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. 10-GEMMASCOPE-RES-16K
    6. 2942
    Prev
    Next
    INDEX
    Explanations

    discussions about accuracy and effectiveness in processes or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Minder
    -0.59
    axs
    -0.59
     Witkin
    -0.58
     Viator
    -0.56
     FormData
    -0.53
     समीक्षाएं
    -0.53
    isContained
    -0.52
    InjectAttribute
    -0.50
    ArrowToggle
    -0.49
     &___
    -0.49
    POSITIVE LOGITS
     enough
    0.98
     juiste
    0.90
     necessary
    0.90
     correct
    0.88
     needed
    0.88
     کافی
    0.85
    enough
    0.85
     correctly
    0.84
     appropriate
    0.83
     adequate
    0.82
    Activations Density 0.323%

    No Known Activations