Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 6146
    Prev
    Next
    INDEX
    Explanations

    aspects of social dynamics and emotional well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     livet
    -0.49
     Interv
    -0.44
    utor
    -0.42
     capelli
    -0.41
    rec
    -0.41
    Interv
    -0.41
     fır
    -0.40
     suces
    -0.40
    px
    -0.40
    Rav
    -0.39
    POSITIVE LOGITS
    ThemeOverlay
    0.93
     AssemblyCulture
    0.87
    twimg
    0.74
     exerted
    0.74
    XmlAccessType
    0.71
     conferred
    0.68
     imparted
    0.68
     manifested
    0.68
    HandlerContext
    0.67
     exercised
    0.66
    Activations Density 0.541%

    No Known Activations