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. MLP Out - 16k
    5. 0-GEMMASCOPE-MLP-16K
    6. 51
    Prev
    Next
    INDEX
    Explanations

    terms related to beverage ingredients and cocktail recipes

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

    terms related to beverages and their descriptions, particularly focusing on rum and cocktails

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    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
    Demografia
    -0.61
     havaianas
    -0.56
    Hauptartikel
    -0.55
     ब्रेकडाउन
    -0.53
    qxd
    -0.53
    НИК
    -0.52
     OMITBAD
    -0.51
    èdia
    -0.50
     capuche
    -0.50
    yarnpkg
    -0.49
    POSITIVE LOGITS
    RenderAtEndOf
    0.67
     surla
    0.58
     attes
    0.48
    limus
    0.48
     anex
    0.48
    POSURE
    0.48
    ignan
    0.47
    ysuckle
    0.47
     confi
    0.45
    Shots
    0.45
    Activations Density 0.760%

    No Known Activations