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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84560
    Prev
    Next
    INDEX
    Explanations

    misconceptions and myths surrounding cultural and historical topics

    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
    ogue
    -0.43
    Viited
    -0.42
    Referanser
    -0.40
    urlpatterns
    -0.37
    closed
    -0.36
    Ar
    -0.36
     reinst
    -0.35
    ORTS
    -0.35
    OGUE
    -0.35
    Hentet
    -0.35
    POSITIVE LOGITS
    RegressionTest
    0.49
     Picchu
    0.47
     >=",
    0.46
    ebenarnya
    0.42
     تضيفلها
    0.42
     widely
    0.42
     termino
    0.41
     Vikipedi
    0.41
     Administrativna
    0.40
    Compartir
    0.40
    Activations Density 0.085%

    No Known Activations