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. 8831
    Prev
    Next
    INDEX
    Explanations

    terms related to pulse justification and measurement

    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
     pulse
    -0.71
     himo
    -0.69
     justify
    -0.68
    */].
    -0.65
     EClass
    -0.65
     BoxFit
    -0.63
    EndGlobalSection
    -0.63
    AndEndTag
    -0.60
    rungsseite
    -0.59
    NameInMap
    -0.59
    POSITIVE LOGITS
     parlé
    0.57
     parallèle
    0.56
     secondaires
    0.54
     StringVar
    0.54
     étoit
    0.54
     professionali
    0.53
     obé
    0.52
     rembour
    0.51
    ঙ্গ
    0.51
     permanentes
    0.50
    Activations Density 0.524%

    No Known Activations