© 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. 1665
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Next," indicating a focus on transitions or upcoming events

    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
    aarrggbb
    -0.74
     Efq
    -0.67
     itſelf
    -0.66
     supplémentaires
    -0.62
     raiſ
    -0.60
     frattempo
    -0.57
     '\\;'
    -0.57
    niająca
    -0.57
     cappello
    -0.56
     ―――――
    -0.55
    POSITIVE LOGITS
     NEXT
    1.10
     Next
    1.07
     next
    1.07
    next
    1.03
    door
    0.98
    Next
    0.98
    NEXT
    0.96
     door
    0.94
    setNext
    0.94
     generation
    0.93
    Activations Density 0.103%

    No Known Activations