© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15880
    Prev
    Next
    INDEX
    Explanations

    references to notable quotes or expressions within written content

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

    Followed by titles or quotations

    np_acts-logits-general · gemini-2.0-flash

    written noteanother quoteanti-nuke epicopening dialogue

    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
    IsMutable
    -0.89
    Personendaten
    -0.74
     HasFactory
    -0.72
     Roskov
    -0.63
    DotNetBar
    -0.60
     ivelany
    -0.60
    reportWebVitals
    -0.59
    Wirtschaft
    -0.58
     propOrder
    -0.57
     Estates
    -0.56
    POSITIVE LOGITS
     Text
    1.27
     Video
    1.14
     Picture
    1.11
     Photo
    1.09
     Letter
    1.08
     Article
    1.07
     Story
    1.04
     Image
    1.02
     Message
    1.01
    Text
    0.97
    Activations Density 0.485%

    No Known Activations