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. 0-GEMMASCOPE-MLP-16K
    6. 36
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "Ca" and its related forms, which likely correspond to a specific chemical or element

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to certain text blocks or headers

    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-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    на
    -1.01
     vectorielle
    -0.76
    Lähteet
    -0.67
    scalatest
    -0.66
     vectorielles
    -0.63
    apimachinery
    -0.62
    casio
    -0.60
    Pranala
    -0.60
    testng
    -0.60
    ziali
    -0.60
    POSITIVE LOGITS
     Федерации
    0.69
    ity
    0.68
    исленность
    0.67
    __(/*!
    0.60
    ly
    0.60
    com
    0.57
    帖最后由
    0.56
    mata
    0.56
    ment
    0.55
    EEEEEEEE
    0.55
    Activations Density 0.126%

    No Known Activations