© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 128520
    Prev
    Next
    INDEX
    Explanations

    intensifiers that emphasize the degree of feelings or opinions

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

    really + verb/auxiliary intensifier

    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
    ContentLoaded
    -0.65
    AutoModerator
    -0.59
    ocate
    -0.57
     informée
    -0.56
    OPC
    -0.52
     TestBed
    -0.52
    InitVars
    -0.52
    sstelle
    -0.50
     Swap
    -0.50
    toko
    -0.49
    POSITIVE LOGITS
    really
    1.74
     really
    1.69
    Really
    1.49
     Really
    1.48
     REALLY
    1.46
     realy
    1.15
     vraiment
    1.13
     realmente
    1.12
     gerçekten
    1.00
     wirklich
    1.00
    Activations Density 0.013%

    No Known Activations