© 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. 12043
    Prev
    Next
    INDEX
    Explanations

    various scents and odors, particularly those that are strong or unpleasant

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

    relating to smell

    np_acts-logits-general · gemini-2.0-flash

    scent, smell, odor

    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
    يكب
    -0.59
    nsito
    -0.45
    (!__
    -0.44
     Jesu
    -0.43
     Jiang
    -0.43
    tagHelperRunner
    -0.43
     Raju
    -0.42
    tifice
    -0.42
    RDP
    -0.42
     Transistor
    -0.41
    POSITIVE LOGITS
     smell
    1.66
     smells
    1.63
     Smell
    1.47
     smelling
    1.45
    smell
    1.42
     scent
    1.42
     smelled
    1.39
    Smell
    1.39
     odeur
    1.38
     odor
    1.37
    Activations Density 0.150%

    No Known Activations