© 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
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 5982
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to procedural and regulatory language, particularly regarding approval processes and document management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ViewImports
    -0.47
     Economía
    -0.36
     étab
    -0.34
     établie
    -0.34
    empereur
    -0.33
     المعيارى
    -0.33
     recovering
    -0.32
     reasoning
    -0.32
     ocupación
    -0.32
     seguido
    -0.31
    POSITIVE LOGITS
    Manbalar
    0.59
     iconLine
    0.57
    ScopeManager
    0.53
     חיצוניים
    0.53
    hoea
    0.51
    bootstrapcdn
    0.49
     محفوظة
    0.48
    cessed
    0.46
    Archie
    0.46
    InputBorder
    0.46
    Activations Density 1.153%

    No Known Activations