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. 20-GEMMASCOPE-RES-16K
    6. 8936
    Prev
    Next
    INDEX
    Explanations

    lines of code that include specific file or library references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xtext
    -0.58
     gyhoeddwyd
    -0.57
    geslacht
    -0.56
    ContentAlignment
    -0.56
    uidado
    -0.56
     dispuesto
    -0.55
     '''
    -0.54
     financières
    -0.54
     juridiques
    -0.54
    userdetails
    -0.53
    POSITIVE LOGITS
    string
    0.55
    limits
    0.53
    vector
    0.51
     $("<
    0.51
    moiselle
    0.51
     $('<
    0.50
    fstream
    0.49
    stdlib
    0.49
    assert
    0.49
    ToBounds
    0.47
    Activations Density 0.087%

    No Known Activations