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. 21-GEMMASCOPE-RES-16K
    6. 7333
    Prev
    Next
    INDEX
    Explanations

    references to coffee and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ogóle
    -0.52
    UseVisualStyle
    -0.48
    deut
    -0.45
    AntiForgeryToken
    -0.43
    </thead>
    -0.43
     LIABLE
    -0.42
     Jerusalén
    -0.42
    ticelli
    -0.42
     עליו
    -0.42
    obald
    -0.40
    POSITIVE LOGITS
     autorytatywna
    0.94
    脚注の使い方
    0.89
     drinkers
    0.76
    sizeCache
    0.75
    adone
    0.73
    aarrggbb
    0.73
    houses
    0.73
     drinker
    0.72
     shop
    0.72
    drinking
    0.71
    Activations Density 0.036%

    No Known Activations