© 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. 21-GEMMASCOPE-RES-16K
    11. 12839
    Prev
    Next
    INDEX
    Explanations

    future tense expressions and indications of intention

    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
    RegistryLite
    -0.71
     المعيارى
    -0.66
     Autónoma
    -0.61
    extAlignment
    -0.61
     Winaray
    -0.60
    cognised
    -0.60
    styleable
    -0.59
     realisation
    -0.59
     BoxDecoration
    -0.59
     HomeComponent
    -0.57
    POSITIVE LOGITS
    modelBuilder
    0.66
     try
    0.59
     gladly
    0.56
     stick
    0.54
     wait
    0.53
     await
    0.53
    fortawesome
    0.51
     keep
    0.51
     возь
    0.50
    再来
    0.49
    Activations Density 0.102%

    No Known Activations