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 - 65k
    5. 18-GEMMASCOPE-MLP-65K
    6. 84
    Prev
    Next
    INDEX
    Explanations

    terms related to fertilizer and its effects on lawn health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.18.hook_mlp_out
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.97
     myſelf
    -0.88
     Efq
    -0.83
    HandlerContext
    -0.80
     Theſe
    -0.80
     purpoſe
    -0.79
     Monfieur
    -0.78
     ſeveral
    -0.78
     itſelf
    -0.77
     themſelves
    -0.76
    POSITIVE LOGITS
     Fer
    0.71
     fertilization
    0.64
    Fer
    0.61
     FERT
    0.60
     fer
    0.59
    fer
    0.59
     fertilizer
    0.59
    NP
    0.57
     fertiliser
    0.55
     fertil
    0.55
    Activations Density 0.261%

    No Known Activations