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. 22-GEMMASCOPE-MLP-16K
    6. 15913
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to statistical methodologies and comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -1.95
    ship
    -1.34
    ski
    -1.23
    ships
    -1.23
    sent
    -1.20
    systems
    -1.19
    solutions
    -1.19
    system
    -1.16
    san
    -1.15
    school
    -1.15
    POSITIVE LOGITS
    es
    0.53
    ン
    0.48
    Хьажоргаш
    0.47
    usermodel
    0.46
    ‌ای
    0.43
     kasarigan
    0.42
    ね
    0.42
     الاطلاع
    0.40
    ening
    0.39
    ASP
    0.39
    Activations Density 1.321%

    No Known Activations