© 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. 116501
    Prev
    Next
    INDEX
    Explanations

    terms related to saltiness or salinity in food context

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

    salt and salty

    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
     noDo
    -0.55
    RequiresApi
    -0.48
     JpaRepository
    -0.47
    SupportActionBar
    -0.45
     Mani
    -0.44
    _))
    -0.43
    __(/*!
    -0.43
    beginTransaction
    -0.43
     Italijanski
    -0.43
    ();)
    -0.43
    POSITIVE LOGITS
    salty
    1.63
     salty
    1.63
     Salty
    1.55
    Salty
    1.54
     salted
    1.00
    咸
    0.71
    鹹
    0.68
     unsalted
    0.65
     saltwater
    0.63
     savory
    0.55
    Activations Density 0.002%

    No Known Activations