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. 5-GEMMASCOPE-RES-16K
    6. 3302
    Prev
    Next
    INDEX
    Explanations

    references to meetings and interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Duff
    -0.72
    Lulu
    -0.68
     Jansen
    -0.67
    ovsky
    -0.65
    ノロ
    -0.65
    cao
    -0.65
     الب
    -0.61
     Swanson
    -0.60
     Ros
    -0.60
    пуляр
    -0.60
    POSITIVE LOGITS
     MEET
    2.28
    meet
    2.23
     Meet
    2.20
    MEET
    2.17
     meet
    2.17
    Meet
    2.12
     meets
    2.07
     Meeting
    1.95
    Meeting
    1.95
     Meets
    1.93
    Activations Density 0.059%

    No Known Activations