© 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. 82845
    Prev
    Next
    INDEX
    Explanations

    Japanese characters or expressions related to omissions or responsibilities

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

    approximately, about, 約, 약

    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
     lumineuse
    -0.40
     fondament
    -0.40
     féminine
    -0.39
     Estamos
    -0.38
     africaine
    -0.38
    Estamos
    -0.38
     goederen
    -0.38
     pitää
    -0.38
     vastaan
    -0.37
     énergétique
    -0.37
    POSITIVE LOGITS
    約
    2.17
    约
    2.03
     約
    1.84
    は約
    1.38
     약
    1.38
    약
    1.18
     approximately
    1.06
     Approximately
    1.05
    Approximately
    1.03
    Approx
    0.96
    Activations Density 0.002%

    No Known Activations