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. 38869
    Prev
    Next
    INDEX
    Explanations

    technical terms associated with mechanisms and efforts related to motion and control

    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
     незавершена
    -0.52
    verwijspagina
    -0.50
    AndroidJUnit
    -0.46
     fountains
    -0.39
    BagLayout
    -0.38
     }{@
    -0.38
     barres
    -0.37
    andra
    -0.37
     Brandt
    -0.37
    Према
    -0.36
    POSITIVE LOGITS
    :✨
    0.66
     שוליים
    0.62
    soft
    0.41
     Autorisations
    0.40
    UrlResolution
    0.40
    sod
    0.38
     tougher
    0.38
    Push
    0.38
     snippetHide
    0.38
    sof
    0.38
    Activations Density 0.038%

    No Known Activations