© 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. 25-GEMMASCOPE-RES-16K
    11. 2814
    Prev
    Next
    INDEX
    Explanations

    phrases that express complex ideas or rhetorical questions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trotzdem
    -0.73
     entanto
    -0.68
     nonetheless
    -0.68
     inoltre
    -0.66
    μως
    -0.65
     nevertheless
    -0.65
     moreover
    -0.64
     therefore
    -0.64
     also
    -0.62
     but
    -0.62
    POSITIVE LOGITS
     Well
    2.06
    Well
    2.03
     well
    1.96
    well
    1.77
     WELL
    1.49
    WELL
    1.46
    Pues
    1.14
     Pues
    1.07
     Hmm
    1.01
     Umm
    1.00
    Activations Density 0.334%

    No Known Activations