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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 8640
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting elements related to document structure and figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    
    -0.88
    ########.
    -0.85
    OGND
    -0.76
     otomatig
    -0.75
    +:+
    -0.73
    principalColumn
    -0.73
     témoig
    -0.73
     TestBed
    -0.70
     queſta
    -0.66
     ſondern
    -0.65
    POSITIVE LOGITS
    center
    0.45
    centerline
    0.39
    C
    0.38
    <thead>
    0.37
     BoxDecoration
    0.36
    Center
    0.35
     Cer
    0.35
      
    0.34
     C
    0.34
     cer
    0.34
    Activations Density 0.075%

    No Known Activations