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. 189
    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
    DoubleQuotes
    -0.54
    lifecycle
    -0.50
    ứng
    -0.48
    amp
    -0.48
    cdnjs
    -0.47
    CompleteListener
    -0.47
    lamic
    -0.47
    tinyos
    -0.47
    lt
    -0.46
    b
    -0.46
    POSITIVE LOGITS
    tvguidetime
    1.07
    IUrlHelper
    0.97
    expandindo
    0.94
    ंदीखरीदारी
    0.91
    GEBURTSDATUM
    0.81
     utafitiHapana
    0.79
     <<<<<<<<<<<<<<
    0.78
    EndInit
    0.76
    parsedMessage
    0.75
     [*]
    0.73
    Activations Density 0.032%

    No Known Activations