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. 8830
    Prev
    Next
    INDEX
    Explanations

    symbols related to comparison operators in programming code

    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
    ⓧ
    -0.89
     محفوظة
    -0.73
    #+#
    -0.69
    AndEndTag
    -0.65
    хьтан
    -0.63
     esternos
    -0.63
     出版
    -0.63
    RenderAtEndOf
    -0.62
    culously
    -0.59
    الإنجليزية
    -0.59
    POSITIVE LOGITS
    aminen
    0.48
    ())),
    0.48
     RIPRODUZIONE
    0.48
     Umfang
    0.47
     thuyết
    0.47
    nungs
    0.44
    mentar
    0.44
    ords
    0.43
     Branca
    0.43
     melody
    0.42
    Activations Density 0.077%

    No Known Activations