© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 490
    Prev
    Next
    INDEX
    Explanations

    negative expressions regarding situations or objects, particularly those involving honey and the use of "nicht" (not) in various contexts

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

    words related to honey and its characteristics in a context that discusses perceptions and interactions

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

    verb chains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Monfieur
    -0.86
     Jefus
    -0.78
     Efq
    -0.70
     houſe
    -0.67
     raiſ
    -0.67
     pleaſure
    -0.66
     whoſe
    -0.63
     itſelf
    -0.62
     reaſon
    -0.62
     ſmall
    -0.61
    POSITIVE LOGITS
    AndroidJUnit
    0.74
    ArgsConstructor
    0.65
     resourceCulture
    0.62
    afficheront
    0.62
    parsedMessage
    0.62
    piram
    0.58
    complexContent
    0.58
     kiện
    0.57
    +#+#
    0.56
    expandindo
    0.55
    Activations Density 0.009%

    No Known Activations