© 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. 8661
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lift" and its variations in the context of physical elevation or improvement

    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
    extAlignment
    -0.83
    ETHING
    -0.76
     gră
    -0.73
    voorbeeld
    -0.72
    rungsseite
    -0.69
     numberWith
    -0.68
    MemoryWarning
    -0.67
     frequenza
    -0.66
    Susie
    -0.66
     cantit
    -0.66
    POSITIVE LOGITS
     lift
    3.19
     Lift
    2.96
     lifts
    2.94
    lift
    2.81
    Lift
    2.79
     lifted
    2.78
     LIFT
    2.78
     lifting
    2.77
     Lifting
    2.48
    lifts
    2.45
    Activations Density 0.088%

    No Known Activations