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. 61064
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be"

    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
     ainfi
    -1.06
     feroit
    -0.99
     étoient
    -0.95
     auroit
    -0.94
     Monfieur
    -0.93
    OGND
    -0.91
     avoient
    -0.90
     plufieurs
    -0.89
     pleaſure
    -0.85
     étoit
    -0.84
    POSITIVE LOGITS
    tvguidetime
    0.69
    hdashline
    0.62
    ↵↵
    0.62
    <eos>
    0.60
    </b>
    0.60
    </blockquote>
    0.59
     M
    0.57
    ↵
    0.57
     A
    0.55
    </i>
    0.54
    Activations Density 0.115%

    No Known Activations