© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 37885
    Prev
    Next
    INDEX
    Explanations

    references to data structures and their attributes

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

    field names and types

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    addContainerGap
    -0.50
    BindingResult
    -0.47
    addGap
    -0.43
     getItemId
    -0.38
    исленность
    -0.37
    Tikang
    -0.37
     للمعارف
    -0.36
    ExtendWith
    -0.36
    makeText
    -0.36
    TableModel
    -0.36
    POSITIVE LOGITS
    SharedDtor
    0.60
     nakalista
    0.60
    CppMethod
    0.49
    istible
    0.48
    ragalactic
    0.47
    ResumeLayout
    0.47
    writeFieldEnd
    0.47
     wikipagina
    0.46
    gucig
    0.46
     dezelve
    0.46
    Activations Density 0.246%

    No Known Activations