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. 0-GEMMASCOPE-MLP-65K
    6. 60962
    Prev
    Next
    INDEX
    Explanations

    instances of blank spaces or unseen characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ​
    -1.43
    ​​
    -1.06
    ​​​​
    -0.97
    ​​​
    -0.97
    </u>
    -0.94
    ​,
    -0.91
     ​
    -0.88
     
    -0.88
    )​
    -0.83
    </s>
    -0.82
    POSITIVE LOGITS
    NameInMap
    0.79
    parsedMessage
    0.69
     őket
    0.68
     dirilis
    0.65
    ttemberg
    0.65
     Affiliations
    0.64
    nocześnie
    0.63
     Monfieur
    0.63
     religieuses
    0.63
    chures
    0.62
    Activations Density 0.052%

    No Known Activations