© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 110286
    Prev
    Next
    INDEX
    Explanations

    terms related to mismatching and matching concepts, particularly in technical or programming 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
     mismatch
    -1.30
    Mismatch
    -1.00
    matched
    -0.59
    matches
    -0.58
     MATCH
    -0.58
    MATCH
    -0.57
     Match
    -0.57
     matches
    -0.52
     Matching
    -0.52
    Match
    -0.52
    POSITIVE LOGITS
    <?
    0.53
     Paglinawan
    0.52
     propOrder
    0.45
    awtextra
    0.44
     <=",
    0.44
    новниш
    0.44
     ویکی‌پدیا
    0.44
    ifolium
    0.41
    LookAnd
    0.40
    Personendaten
    0.40
    Activations Density 0.003%

    No Known Activations