© 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. 91004
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to adding or including elements in a programming context

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

    adding or addition

    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
    stdc
    -0.60
    gameState
    -0.59
     CGPoint
    -0.52
     IActionResult
    -0.50
    gettime
    -0.49
    annica
    -0.48
     fontWeight
    -0.48
     dezelve
    -0.47
    currentThread
    -0.46
     ------------
    -0.46
    POSITIVE LOGITS
     additions
    0.88
     Add
    0.87
     ajout
    0.86
     add
    0.84
    Add
    0.82
     Addition
    0.81
     addition
    0.81
    Adding
    0.81
    ToAdd
    0.79
     added
    0.79
    Activations Density 0.047%

    No Known Activations