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. 6-GEMMASCOPE-MLP-16K
    6. 111
    Prev
    Next
    INDEX
    Explanations

    terms related to anatomical abnormalities and medical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     siglas
    -0.52
    rippa
    -0.50
    phur
    -0.50
    GeneratedValue
    -0.50
    CGSize
    -0.50
    croll
    -0.49
    írus
    -0.49
     thay
    -0.48
    सन्दर्भ
    -0.48
    Izvori
    -0.47
    POSITIVE LOGITS
     yours
    0.68
     lohnt
    0.66
     faſt
    0.63
     vinted
    0.63
     meantime
    0.63
     Inters
    0.61
     Thine
    0.60
     ſt
    0.60
    šech
    0.60
     eyel
    0.60
    Activations Density 0.337%

    No Known Activations