© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15439
    Prev
    Next
    INDEX
    Explanations

    concepts related to refuge and relaxation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    relaxation or stress reduction

    np_acts-logits-general · gemini-2.0-flash

    relax and unwind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     numerus
    -0.59
    χρι
    -0.49
     })}
    -0.45
    ughty
    -0.44
    헌
    -0.44
    twimg
    -0.44
     ketat
    -0.44
    月号
    -0.44
     createState
    -0.43
     ;(
    -0.43
    POSITIVE LOGITS
     relaxation
    1.39
     relax
    1.26
     relaxing
    1.26
    relax
    1.24
     Relaxation
    1.23
    Relax
    1.20
     relaxes
    1.19
     Relax
    1.17
     stress
    1.15
     unwind
    1.12
    Activations Density 0.140%

    No Known Activations