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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 12806
    Prev
    Next
    INDEX
    Explanations

    references to social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     дописавши
    -0.70
     estimés
    -0.68
    routeProvider
    -0.68
    WaitGroup
    -0.66
    XmlAccessType
    -0.65
    UnsafeEnabled
    -0.63
    yntaxException
    -0.62
    ellites
    -0.62
    lgari
    -0.61
    ValueStyle
    -0.60
    POSITIVE LOGITS
     media
    1.25
    media
    1.02
     Media
    1.00
     MEDIA
    0.91
    Media
    0.88
    MEDIA
    0.85
     mídia
    0.82
     medier
    0.80
     médias
    0.80
     medias
    0.79
    Activations Density 0.072%

    No Known Activations