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. 100
    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
     تضيفلها
    -0.83
    KURZBESCHREIBUNG
    -0.71
    GenerationType
    -0.69
    +#+#
    -0.69
    mybatisplus
    -0.67
     Dietz
    -0.67
     مشين
    -0.66
     vastaan
    -0.65
    AndEndTag
    -0.64
    uevos
    -0.63
    POSITIVE LOGITS
    RegressionTest
    0.63
    I
    0.52
    i
    0.50
     I
    0.49
    pl
    0.48
     thank
    0.47
    ok
    0.46
    thank
    0.45
     thanking
    0.45
    black
    0.45
    Activations Density 0.038%

    No Known Activations