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. 109834
    Prev
    Next
    INDEX
    Explanations

    references to legal and law enforcement terms and situations

    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
    StoryboardSegue
    -0.60
     calls
    -0.55
     call
    -0.55
     Calls
    -0.54
     calling
    -0.53
     насељу
    -0.52
    calls
    -0.48
    BeginContext
    -0.48
    ьаж
    -0.47
    calling
    -0.46
    POSITIVE LOGITS
    rim
    0.41
    typeorm
    0.39
    Dichloroethene
    0.39
    posedge
    0.39
    CppMethod
    0.38
    ortun
    0.38
    BagLayout
    0.37
    localctx
    0.37
     Wiktionnaire
    0.36
     улыб
    0.36
    Activations Density 0.030%

    No Known Activations