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. 55
    Prev
    Next
    INDEX
    Explanations

    specific instructions related to event planning and dining

    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
     attending
    -1.17
     attend
    -1.14
     attends
    -1.11
     Attend
    -1.08
     attendance
    -1.07
     Attending
    -1.05
    Attend
    -1.04
     attended
    -1.02
     Attendance
    -0.91
    attend
    -0.90
    POSITIVE LOGITS
    copyFrom
    0.51
    CodeDom
    0.50
    ="#"><
    0.47
     Infórmanos
    0.42
    хли
    0.41
     Ped
    0.41
    stdc
    0.40
    ýš
    0.39
    阶
    0.38
     ped
    0.38
    Activations Density 0.090%

    No Known Activations