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. 138
    Prev
    Next
    INDEX
    Explanations

    biographical details about individuals

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

    biographical details about people's family backgrounds, particularly parents and their origins.

    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
     lifted
    -0.36
     lift
    -0.33
     danger
    -0.33
     spot
    -0.32
     contract
    -0.32
     hit
    -0.31
     Zeitraum
    -0.31
    illerato
    -0.31
     criterios
    -0.31
     Vertrag
    -0.31
    POSITIVE LOGITS
    تقاوى
    0.85
    ViewImports
    0.77
     للاسماء
    0.71
     kasarigan
    0.66
    󠁴
    0.64
    __":
    0.63
    verwijspagina
    0.63
    Демографія
    0.62
     CreateTagHelper
    0.61
     Meksiku
    0.60
    Activations Density 0.202%

    No Known Activations