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. 46
    Prev
    Next
    INDEX
    Explanations

    references to companies or organizations that are described as 'leading'

    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
     leading
    -1.16
    leading
    -0.97
     Leading
    -0.89
    Leading
    -0.82
     leads
    -0.66
     lead
    -0.65
    lead
    -0.55
     led
    -0.52
    tema
    -0.51
     has
    -0.50
    POSITIVE LOGITS
     الحره
    0.83
     $_"
    0.82
    GOTREF
    0.80
     useAppContext
    0.79
    Datuak
    0.75
    Hentet
    0.74
    oa̍t
    0.73
     Majefty
    0.73
    KommentareTeilen
    0.71
    ,:),
    0.71
    Activations Density 0.009%

    No Known Activations