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. 39
    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
     
    -0.67
     a
    -0.61
     to
    -0.53
     my
    -0.50
     vertes
    -0.50
     for
    -0.49
     some
    -0.49
    '
    -0.48
    <eos>
    -0.48
     the
    -0.48
    POSITIVE LOGITS
     للمعارف
    1.09
     تانيه
    1.00
     Normdatei
    0.90
     ddelweddau
    0.86
     متعلقه
    0.85
     فريبيس
    0.84
    ffl
    0.82
     Cytometry
    0.81
    Hentet
    0.80
     FontWeight
    0.79
    Activations Density 0.034%

    No Known Activations