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. 1223
    Prev
    Next
    INDEX
    Explanations

    references to historical inventions and their inventors

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

    Years (four digits)

    np_acts-logits-general · gemini-2.0-flash

    years, names, and specific inventions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     BaseActivity
    -0.60
    VYMaps
    -0.59
    ésultats
    -0.58
     CSC
    -0.57
     ppb
    -0.57
    globo
    -0.56
    ſchaft
    -0.56
     PSD
    -0.56
     ſind
    -0.55
    哋
    -0.55
    POSITIVE LOGITS
    ksikon
    0.39
     CreateTagHelper
    0.38
    SequentialGroup
    0.35
    vician
    0.34
     iconTwitter
    0.33
     esternos
    0.33
     precisión
    0.31
     aprovecha
    0.31
     Widerspruch
    0.30
    tagHelperRunner
    0.29
    Activations Density 0.325%

    No Known Activations