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. 61074
    Prev
    Next
    INDEX
    Explanations

    instances of the word "there."

    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
    tvguidetime
    -1.07
     متعلقه
    -0.96
    expandindo
    -0.91
     utafitiHapana
    -0.87
     nahilalakip
    -0.86
    IntoConstraints
    -0.85
     disambiguazione
    -0.81
    rungsseite
    -0.81
     CanadaChoose
    -0.79
     surla
    -0.77
    POSITIVE LOGITS
     Monfieur
    0.76
    <bos>
    0.71
     Theſe
    0.69
     quæ
    0.65
     Efq
    0.61
     emperador
    0.59
     Diſ
    0.59
     Könige
    0.58
     chrétien
    0.58
     αὐτ
    0.57
    Activations Density 0.090%

    No Known Activations