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. 109763
    Prev
    Next
    INDEX
    Explanations

    references to artistic or creative works

    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
     piece
    -1.60
     Piece
    -1.39
     pieces
    -1.31
    piece
    -1.28
     PIECE
    -1.27
     Pieces
    -1.21
    Piece
    -1.09
     pieza
    -1.07
    Pieces
    -1.05
    PIECE
    -1.05
    POSITIVE LOGITS
     <=",
    0.45
    CharStream
    0.42
    Референце
    0.41
    MarshalTo
    0.41
    principalTable
    0.40
    Życiorys
    0.39
    новниш
    0.38
     exchange
    0.38
    JspWriter
    0.38
    𝗫
    0.37
    Activations Density 0.002%

    No Known Activations