© 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. 3-GEMMASCOPE-RES-16K
    11. 13197
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate emphasis or focus on specific topics or ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     solution
    -0.57
    irvana
    -0.56
     trick
    -0.54
    tır
    -0.53
     Martino
    -0.53
    б
    -0.52
    ro
    -0.51
    Coo
    -0.51
     next
    -0.50
     kwi
    -0.50
    POSITIVE LOGITS
     emphasis
    2.59
     Emphasis
    2.48
     emphasise
    2.33
     emphasize
    2.26
     emphas
    2.23
     emphasizing
    2.21
     emphasised
    2.17
     emphasized
    2.13
    emphasis
    2.11
     emphasizes
    2.09
    Activations Density 0.107%

    No Known Activations