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. 18-GEMMASCOPE-RES-16K
    6. 800
    Prev
    Next
    INDEX
    Explanations

    chemical reactions and their related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "The" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    "The" followed by a noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.85
     يتيمه
    -0.73
     banners
    -0.70
    IntoConstraints
    -0.69
     intptr
    -0.69
    تقاوى
    -0.68
    +:+
    -0.68
    )•
    -0.66
    mybatisplus
    -0.66
    .[/
    -0.65
    POSITIVE LOGITS
     $\
    0.97
     ${\
    0.83
     $
    0.83
     $(
    0.70
     esetén
    0.66
     (
    0.62
     computa
    0.62
     data
    0.61
     obtained
    0.61
     ${
    0.61
    Activations Density 5.684%

    No Known Activations