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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 201
    Prev
    Next
    INDEX
    Explanations

    commands and actions related to navigating a user interface or system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    numbers and dates, especially years from the early 20th century.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
    MLLoader
    -0.69
    TagMode
    -0.65
    Datuak
    -0.61
     فريبيس
    -0.58
    ImageContext
    -0.57
    HasIndex
    -0.53
    IBOutlet
    -0.53
    Tikang
    -0.51
    cayaan
    -0.51
    ulgação
    -0.50
    POSITIVE LOGITS
     aapt
    0.36
     Sem
    0.33
     lenker
    0.32
     sem
    0.31
    Sem
    0.30
     reckon
    0.30
     voci
    0.30
    IsMutable
    0.30
    CO
    0.29
     Pd
    0.29
    Activations Density 0.020%

    No Known Activations