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. 61017
    Prev
    Next
    INDEX
    Explanations

    instances of the word "question."

    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
    InvalidProtocol
    -0.85
    évaluateur
    -0.73
     发表于
    -0.71
     invokingState
    -0.71
     cherchés
    -0.62
    VersionUID
    -0.61
    ThroughAttribute
    -0.58
    LookAnd
    -0.57
     occurred
    -0.55
    핍
    -0.54
    POSITIVE LOGITS
    ="#"><
    0.60
     turísticos
    0.57
     prêts
    0.56
     soigneusement
    0.55
     pesado
    0.55
    väl
    0.55
    '`
    0.54
     chrétien
    0.54
     lentement
    0.54
     refroid
    0.54
    Activations Density 0.031%

    No Known Activations