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. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K__L0-22
    6. 23
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -0.93
     itſelf
    -0.84
    ſelf
    -0.82
    ंदीखरीदारी
    -0.79
    tvguidetime
    -0.78
     myſelf
    -0.77
     fevere
    -0.77
    contentLoaded
    -0.76
     ſtate
    -0.75
     '\\;'
    -0.75
    POSITIVE LOGITS
    []
    0.62
     aux
    0.57
     i
    0.55
     Nature
    0.54
     result
    0.53
     nature
    0.52
     Ex
    0.51
     p
    0.50
    inf
    0.50
     itu
    0.49
    Activations Density 0.139%

    No Known Activations