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. 18-GEMMASCOPE-MLP-65K
    6. 58
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the phrase "members of" in relation to various groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.18.hook_mlp_out
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.65
    rungsseite
    -0.64
    InputLabel
    -0.52
    HtmlAttribute
    -0.48
    SizeMode
    -0.46
    DataContract
    -0.43
    AutoField
    -0.42
     industriale
    -0.42
    gag
    -0.42
     organist
    -0.41
    POSITIVE LOGITS
    TintMode
    0.65
    Билгалдахарш
    0.63
    Dziękuję
    0.62
    Πηγές
    0.60
    ACIAS
    0.58
    슷
    0.57
    atiles
    0.57
     utafiti
    0.56
    tanleria
    0.55
    schuh
    0.55
    Activations Density 0.034%

    No Known Activations