© 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. 4936
    Prev
    Next
    INDEX
    Explanations

    references to "Ambrosia" or related products

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

    starting with "Amb" or containing "mb"

    np_acts-logits-general · gemini-2.0-flash

    ambles and words starting with 'amb'

    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
    Reviewed
    -0.59
    endregion
    -0.50
    gameserver
    -0.47
    ="@+
    -0.45
    eri
    -0.45
    frutar
    -0.45
    enumi
    -0.45
    Auswahl
    -0.44
    UNRELATED
    -0.43
     chiuso
    -0.43
    POSITIVE LOGITS
     betweenstory
    0.77
    orghini
    0.64
    TintMode
    0.63
    cokinetics
    0.62
    AccessorTable
    0.61
     ISNI
    0.60
     Amb
    0.58
     متعلقه
    0.58
    ushed
    0.57
     ComVisible
    0.55
    Activations Density 0.145%

    No Known Activations