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. 1-GEMMASCOPE-RES-16K
    6. 14771
    Prev
    Next
    INDEX
    Explanations

    references to oxalate and its related measurements in biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.86
     незавершена
    -0.73
    bootstrapcdn
    -0.69
    willi
    -0.64
    róleo
    -0.63
    Arturo
    -0.63
     McGuire
    -0.62
     leg
    -0.61
     Miko
    -0.61
    ReusableCell
    -0.60
    POSITIVE LOGITS
     blossom
    0.82
     Luxor
    0.80
     Zen
    0.78
     oxalate
    0.78
     Luxe
    0.77
     blossoms
    0.75
     Lux
    0.74
     soak
    0.73
     Ox
    0.72
     bloom
    0.71
    Activations Density 3.318%

    No Known Activations