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. 8961
    Prev
    Next
    INDEX
    Explanations

    terms related to improving diagnostic processes and criteria in healthcare

    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
    mapreduce
    -0.52
     ModelExpression
    -0.49
    ntk
    -0.45
    zus
    -0.44
    Naphthalene
    -0.43
    Földrajzportál
    -0.42
     Inti
    -0.41
     Offisielt
    -0.41
     filtrate
    -0.41
    itaria
    -0.40
    POSITIVE LOGITS
    imageshack
    0.71
    TypedDataSet
    0.69
     שוליים
    0.64
    EndGlobalSection
    0.64
    TagHelper
    0.59
    Personensuche
    0.59
    Помо
    0.57
    terness
    0.57
     MotionEvent
    0.57
     <<<<<<<<<<<<<<
    0.56
    Activations Density 0.382%

    No Known Activations