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. 120
    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
     Brito
    -0.66
    StrictEqual
    -0.62
     Архивировано
    -0.62
     DriverManager
    -0.62
    Perché
    -0.61
    mergeFrom
    -0.59
    意思
    -0.58
    scrollTop
    -0.58
     consum
    -0.58
     I
    -0.57
    POSITIVE LOGITS
     notes
    1.59
     note
    1.54
     Notes
    1.53
     NOTE
    1.43
     Note
    1.42
     Nota
    1.34
     NOTES
    1.34
    notes
    1.30
    Note
    1.30
    note
    1.28
    Activations Density 0.051%

    No Known Activations