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. 20-GEMMASCOPE-RES-16K
    6. 2909
    Prev
    Next
    INDEX
    Explanations

    items of clothing and their descriptions

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

    Types of clothing

    np_acts-logits-general · gemini-2.0-flash

    items of clothing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    рей
    -0.45
     nakalista
    -0.45
     Domestic
    -0.44
     domestic
    -0.43
    URUS
    -0.42
     obec
    -0.42
    })();
    -0.42
    agre
    -0.42
    ppan
    -0.42
    using
    -0.42
    POSITIVE LOGITS
     worn
    1.07
     wearer
    0.94
     Worn
    0.79
    worn
    0.69
     Zwiebel
    0.68
     donned
    0.68
     encendido
    0.64
     diken
    0.63
     Wear
    0.62
     itſelf
    0.62
    Activations Density 0.174%

    No Known Activations