© 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. 18-GEMMASCOPE-RES-16K
    11. 57
    Prev
    Next
    INDEX
    Explanations

    expressions of positive emotions or sentiments

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

    Expressing personal feelings or opinions

    np_acts-logits-general · gemini-2.0-flash

    glad we were able to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     niestety
    -0.62
     fascinating
    -0.62
     sadly
    -0.61
    encji
    -0.59
     famously
    -0.58
     notoriously
    -0.57
     unfortunately
    -0.56
     enviable
    -0.55
     hilarious
    -0.55
     unbearable
    -0.54
    POSITIVE LOGITS
     finally
    0.80
     Finally
    0.72
    Finally
    0.71
    finally
    0.69
     finalmente
    0.68
     able
    0.66
     AssemblyTitle
    0.65
     ویکی‌پدیا
    0.65
    GeoNames
    0.63
     наконец
    0.63
    Activations Density 0.223%

    No Known Activations