Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21879
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting related to legal or formal documents

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Искәрмәләр
    -0.52
    Дереккөздер
    -0.48
    seus
    -0.46
    Сим
    -0.46
    ADELPHIA
    -0.45
    positor
    -0.45
    abbix
    -0.44
    scars
    -0.44
    cheduler
    -0.43
    ReusableCell
    -0.43
    POSITIVE LOGITS
    ValueStyle
    0.69
    CompilerServices
    0.49
    +#+
    0.48
     pouvoit
    0.43
     berdua
    0.42
    PerformLayout
    0.41
    tonode
    0.41
     testigos
    0.39
    Бахар
    0.38
     recevez
    0.38
    Activations Density 0.002%

    No Known Activations