© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 8779
    Prev
    Next
    INDEX
    Explanations

    descriptive terms and phrases related to food quality and dining experiences

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

    Preceding positive sentiment words

    np_acts-logits-general · gemini-2.0-flash

    positive sentences start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.68
    Personensuche
    -0.66
    zzleHttp
    -0.64
     henceforth
    -0.63
     hereinafter
    -0.61
    styleType
    -0.61
    parency
    -0.60
    ScopeManager
    -0.60
     Obrador
    -0.59
    ImageContext
    -0.58
    POSITIVE LOGITS
     nice
    0.83
     Friendly
    0.81
    lots
    0.79
     lots
    0.79
     friendly
    0.77
     great
    0.76
    Friendly
    0.75
    nice
    0.75
     very
    0.75
     plenty
    0.74
    Activations Density 0.043%

    No Known Activations