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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 29502
    Prev
    Next
    INDEX
    Explanations

    punctuation related to parentheses and nested expressions

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

    programming language syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kommission
    -0.33
     hopefully
    -0.33
    queado
    -0.33
     encantó
    -0.32
     mies
    -0.32
     idéia
    -0.32
    do
    -0.32
     dé
    -0.32
    kenstock
    -0.32
     préparé
    -0.32
    POSITIVE LOGITS
     AssemblyVersion
    0.69
     bezeichneter
    0.63
    CloseOperation
    0.63
    IBOutlet
    0.63
    AddWithValue
    0.62
    principalColumn
    0.62
     JpaRepository
    0.61
     nahilalakip
    0.60
    HasForeignKey
    0.59
     viewWillAppear
    0.59
    Activations Density 0.001%

    No Known Activations