© 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. 9-GEMMASCOPE-RES-131K
    11. 35416
    Prev
    Next
    INDEX
    Explanations

    references to locations and technical terms related to semiconductor devices and processes

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

    DBS, CMOS, Heathrow, DHL, NSIndexPath

    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
     rústico
    -0.36
     tilbage
    -0.36
     sintético
    -0.35
    krát
    -0.35
    Voltaje
    -0.32
    Referencie
    -0.32
     état
    -0.32
    arrière
    -0.32
    lepší
    -0.31
    fertigen
    -0.31
    POSITIVE LOGITS
     Heathrow
    1.34
     HSBC
    1.28
     DHL
    0.97
    DHL
    0.87
     Gatwick
    0.79
     DBS
    0.78
    TestBed
    0.75
    DBS
    0.70
    execSQL
    0.65
     spender
    0.63
    Activations Density 0.001%

    No Known Activations