© 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. 1862
    Prev
    Next
    INDEX
    Explanations

    expressions related to emotions and social dynamics

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

    something is "real" or "simple"

    np_acts-logits-general · gemini-2.0-flash

    really actually

    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
    SourceChecksum
    -0.67
    WebElementEntity
    -0.62
    parsedMessage
    -0.59
     Reſ
    -0.57
    RuleContext
    -0.55
     consultato
    -0.55
    Diweddarwch
    -0.54
    loride
    -0.54
     CreateTagHelper
    -0.54
    ύτε
    -0.49
    POSITIVE LOGITS
     really
    3.33
    really
    2.95
    Really
    2.69
     Really
    2.68
     realmente
    2.17
     REALLY
    2.08
     realy
    1.94
     vraiment
    1.93
     wirklich
    1.90
     actually
    1.85
    Activations Density 0.400%

    No Known Activations