© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3140
    Prev
    Next
    INDEX
    Explanations

    references to buffets and mandates related to health care policies

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

    "buffet" or "mandate"

    np_acts-logits-general · gemini-2.0-flash

    affordability and choice

    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
     enfans
    -0.49
    enderror
    -0.47
     fön
    -0.44
    SuccessListener
    -0.44
    verwijspagina
    -0.43
    ésultat
    -0.42
    diciones
    -0.42
    rungsseite
    -0.41
     scaricare
    -0.41
     triko
    -0.40
    POSITIVE LOGITS
     buffet
    0.64
    buffet
    0.50
     Buffet
    0.47
     propOrder
    0.46
     CreateTagHelper
    0.43
    自助
    0.41
    TagMode
    0.39
    ❋
    0.39
    OGND
    0.37
     sideboard
    0.36
    Activations Density 0.125%

    No Known Activations