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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109816
    Prev
    Next
    INDEX
    Explanations

    mentions of "Crane" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crane
    -1.83
     Crane
    -1.82
    Crane
    -1.73
     cranes
    -1.63
    crane
    -1.56
     Cranes
    -1.39
     Cran
    -0.79
    cran
    -0.74
     kran
    -0.70
    Cran
    -0.69
    POSITIVE LOGITS
    awtextra
    0.55
    KURZBESCHREIBUNG
    0.49
    enciaga
    0.42
    soka
    0.42
    下载附件
    0.41
    呼
    0.41
    ReusableCell
    0.40
     stanovnika
    0.40
    bró
    0.40
    市镇
    0.40
    Activations Density 0.001%

    No Known Activations