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. 4-GEMMASCOPE-MLP-65K
    6. 63
    Prev
    Next
    INDEX
    Explanations

    terms related to visas and immigration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     visa
    -1.99
     Visa
    -1.73
     visas
    -1.71
    Visa
    -1.69
    visa
    -1.41
     VISA
    -1.38
    VISA
    -1.13
    签证
    -0.89
    Immigration
    -0.70
     immigration
    -0.66
    POSITIVE LOGITS
    Попис
    0.60
    BeginContext
    0.55
    winning
    0.53
    GEBURTS
    0.52
    moveToFirst
    0.52
     ujednoznacz
    0.51
    المكان
    0.49
    ICIOS
    0.48
    ingway
    0.48
    elseif
    0.48
    Activations Density 0.015%

    No Known Activations