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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 1-GEMMASCOPE-MLP-16K
    6. 8950
    Prev
    Next
    INDEX
    Explanations

    elements relating to challenges and aspirations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     internetowa
    -0.68
    المناصب
    -0.63
    isement
    -0.58
    Élet
    -0.57
    最快更新
    -0.56
     Chwiliwch
    -0.56
    SUCCEEDED
    -0.55
    GMENT
    -0.54
     Sucher
    -0.54
    новништво
    -0.53
    POSITIVE LOGITS
    おきます
    0.53
    epam
    0.52
    InjectAttribute
    0.50
    usercontent
    0.49
    antra
    0.49
     Platon
    0.48
    Application
    0.48
    SceneManagement
    0.47
    ensity
    0.47
     butterknife
    0.47
    Activations Density 0.142%

    No Known Activations