© 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. 4-GEMMASCOPE-RES-16K
    11. 15636
    Prev
    Next
    INDEX
    Explanations

    expressions of emphasis or intensity in opinions and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Christiansen
    -0.78
     Shades
    -0.77
     Boswell
    -0.76
     storici
    -0.75
     perpétu
    -0.75
     Wiseman
    -0.75
     vertes
    -0.74
     nationales
    -0.74
     Dodson
    -0.74
     Kowal
    -0.74
    POSITIVE LOGITS
     really
    2.54
    really
    2.24
     Really
    2.19
    Really
    2.09
     REALLY
    2.05
     realy
    1.78
     vraiment
    1.28
     realmente
    1.21
     truly
    1.18
     wirklich
    1.17
    Activations Density 0.056%

    No Known Activations