© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 100546
    Prev
    Next
    INDEX
    Explanations

    colons and double colons, indicating namespaces or scope resolution in programming contexts

    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
    uxxxx
    -0.74
     JpaRepository
    -0.56
     <>",
    -0.55
    UrlResolution
    -0.54
    AutoField
    -0.53
    XmlAccessorType
    -0.51
    ParallelGroup
    -0.49
    httphttps
    -0.48
    GenerationType
    -0.47
    PMailer
    -0.45
    POSITIVE LOGITS
    __(/*!
    0.62
    (::
    0.45
    fjspx
    0.43
     purpoſe
    0.43
    RegistryLite
    0.41
    leggen
    0.40
     handleClick
    0.40
     دیکھیے
    0.40
    ThroughAttribute
    0.39
     fubject
    0.39
    Activations Density 0.003%

    No Known Activations