Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 6579
    Prev
    Next
    INDEX
    Explanations

    the word "used" in various contexts, indicating a focus on usage or application

    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
     myſelf
    -0.78
    mybatisplus
    -0.77
     houſe
    -0.76
     fubject
    -0.76
     ſeveral
    -0.72
     pleaſure
    -0.70
     متعلقه
    -0.69
     perſon
    -0.69
     ſtate
    -0.68
     становника
    -0.67
    POSITIVE LOGITS
     used
    0.85
    USED
    0.83
    nonumber
    0.77
    used
    0.72
     USED
    0.71
    Used
    0.68
     Used
    0.68
     का
    0.56
     يتيمه
    0.53
    HtmlAttribute
    0.53
    Activations Density 0.114%

    No Known Activations