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 - 65k
    5. 4-GEMMASCOPE-MLP-65K
    6. 58
    Prev
    Next
    INDEX
    Explanations

    terms related to the ease or difficulty of processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_4/width_65k/average_l0_66
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.4.hook_mlp_out
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     transfieras
    -0.90
     easy
    -0.77
     faciles
    -0.73
    TagMode
    -0.73
    easy
    -0.69
     itſelf
    -0.68
    Easy
    -0.65
     fácil
    -0.65
    ſelf
    -0.64
     easily
    -0.63
    POSITIVE LOGITS
     AssemblyTitle
    0.52
    endpush
    0.50
     ioutil
    0.50
    lichter
    0.49
     localObject
    0.47
    didSet
    0.46
     endforeach
    0.45
    CompilerServices
    0.45
    ettare
    0.44
    POSED
    0.43
    Activations Density 0.020%

    No Known Activations