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. 22-GEMMASCOPE-MLP-16K
    6. 15813
    Prev
    Next
    INDEX
    Explanations

    instances of the word "come" and related terms reflecting arrival or initiation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.81
    MarshalTo
    -0.69
     Sigmund
    -0.69
     itſelf
    -0.68
     olympiques
    -0.68
    ]='\
    -0.67
     MyBatis
    -0.66
    kloped
    -0.66
     ModelExpression
    -0.66
    TemporalType
    -0.66
    POSITIVE LOGITS
    MLLoader
    0.59
     par
    0.52
     at
    0.52
     en
    0.50
     play
    0.47
     through
    0.46
     hit
    0.46
     En
    0.45
     drink
    0.45
     Par
    0.44
    Activations Density 0.075%

    No Known Activations