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. 21-GEMMASCOPE-RES-16K
    6. 905
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental actions and their implications

    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
     Kontext
    -0.98
     contextos
    -0.81
     контек
    -0.78
     sostenibilidad
    -0.78
     contexto
    -0.76
     Behaviors
    -0.75
     culturelles
    -0.74
     behaviours
    -0.71
    ustainable
    -0.71
     entornos
    -0.70
    POSITIVE LOGITS
     mengadakan
    0.75
     собою
    0.67
     practically
    0.63
     giebt
    0.59
     definite
    0.58
     groote
    0.57
     Practically
    0.57
    furter
    0.56
     specialmente
    0.56
    BoxShadow
    0.56
    Activations Density 0.872%

    No Known Activations