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 - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8759
    Prev
    Next
    INDEX
    Explanations

    elements related to web development and software licenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -1.24
     ModelExpression
    -1.13
     Italijani
    -1.03
    GEBURTSDATUM
    -0.97
     disambiguazione
    -0.96
    +#+#
    -0.95
     tartalomajánló
    -0.95
    Tikang
    -0.95
    Vidite
    -0.93
    rungsseite
    -0.92
    POSITIVE LOGITS
    ailleurs
    0.57
     też
    0.53
     respectivement
    0.49
    んと
    0.48
    ../../
    0.48
     vidrio
    0.46
    Kami
    0.44
     couvert
    0.44
    Holo
    0.44
     demander
    0.43
    Activations Density 0.505%

    No Known Activations