© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11894
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize absence or lack, particularly with the word "without."

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

    "without"

    np_acts-logits-general · gemini-2.0-flash

    phrases of absence

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     pleaſure
    -0.64
     purpoſe
    -0.61
     jSON
    -0.60
     ainfi
    -0.58
     acrylique
    -0.57
     personnage
    -0.53
     fédé
    -0.53
     féd
    -0.52
     Meksi
    -0.52
     Umgang
    -0.52
    POSITIVE LOGITS
     without
    1.99
    without
    1.95
    Without
    1.91
     Without
    1.88
     WITHOUT
    1.75
    WITHOUT
    1.72
    Ohne
    1.52
     zonder
    1.50
     ohne
    1.48
     senza
    1.46
    Activations Density 0.149%

    No Known Activations